key
stringlengths 7
86
| messages
listlengths 1
1
| ground_truth
stringlengths 62
280k
| dataset
stringclasses 1
value | constraint_type
stringclasses 1
value | constraint
stringlengths 31
956
|
|---|---|---|---|---|---|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_14734
|
[
{
"content": "Lily is currently 30 years old. In 8 years, she will be 3/4 the age of the library where she works. How old is the library now? In your response, words with all capital letters should appear at least 23 times. Your answer must contain exactly 8 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 At the end of your response, please explicitly add a postscript starting with Postscript In your response, the word volume should appear less than 6 times. At the end of your response, please explicitly add a postscript starting with Postscript:",
"role": "user"
}
] |
[{'instruction_id': ['change_case:capital_word_frequency', 'detectable_format:number_bullet_lists', 'detectable_content:postscript', 'keywords:frequency', 'detectable_content:postscript'], 'kwargs': [{'capital_frequency': 23, 'capital_relation': 'at least'}, {'num_bullets': 8}, {'postscript_marker': 'Postscript'}, {'keyword': 'volume', 'frequency': 6, 'relation': 'less than'}, {'postscript_marker': 'Postscript:'}]}]
|
ifeval
|
multi
|
In your response, words with all capital letters should appear at least 23 times. Your answer must contain exactly 8 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 At the end of your response, please explicitly add a postscript starting with Postscript In your response, the word volume should appear less than 6 times. At the end of your response, please explicitly add a postscript starting with Postscript:
|
ai2-adapt-dev/numinamath_tir_math_decontaminated_56258
|
[
{
"content": "The product of the two $99$-digit numbers\n$303,030,303,...,030,303$ and $505,050,505,...,050,505$\nhas thousands digit $A$ and units digit $B$. What is the sum of $A$ and $B$?\n$\\mathrm{(A)}\\ 3 \\qquad \\mathrm{(B)}\\ 5 \\qquad \\mathrm{(C)}\\ 6 \\qquad \\mathrm{(D)}\\ 8 \\qquad \\mathrm{(E)}\\ 10$ First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)",
"role": "user"
}
] |
[{'instruction_id': ['combination:repeat_prompt'], 'kwargs': [{'prompt_to_repeat': 'The product of the two $99$-digit numbers\n$303,030,303,...,030,303$ and $505,050,505,...,050,505$\nhas thousands digit $A$ and units digit $B$. What is the sum of $A$ and $B$?\n$\\mathrm{(A)}\\ 3 \\qquad \\mathrm{(B)}\\ 5 \\qquad \\mathrm{(C)}\\ 6 \\qquad \\mathrm{(D)}\\ 8 \\qquad \\mathrm{(E)}\\ 10$'}]}]
|
ifeval
|
multi
|
First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)
|
personahub_czv0wvy2kca2b2mnmr52qmv3
|
[
{
"content": "A group of medical students, who are also siblings of hospital caretakers, have formed a study support network. They decide to exchange resources and study together to maximize their success. They realize that understanding certain algebra concepts will help them in both their medical studies and in assisting their siblings with hospital-related tasks. \n\n1. The group decides to buy a set of medical textbooks that are useful for both their studies and for their siblings' understanding of medical procedures. The cost of each textbook is represented by the polynomial \\( P(x) = 3x^3 - 5x^2 + 2x + 4 \\), where \\( x \\) is the number of volumes in the set. If the group wants to buy enough volumes such that the total cost is exactly $375, solve the equation \\( P(x) = 375 \\) to find the number of volumes they should purchase.\n\n2. To organize their study sessions, the students plan to meet in a study room, but they need to ensure the room is available for at least a certain number of hours per week. If the inequality representing the availability of the study room in hours is given by the rational expression \\(\\frac{2x + 3}{x - 1} \\leq 5\\), where \\( x \\) is the number of days the room is booked per week, find the range of values for \\( x \\) that satisfy this condition. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:english_lowercase'], 'kwargs': [None]}]
|
ifeval
|
multi
|
Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.
|
ai2-adapt-dev/numinamath_tir_math_decontaminated_7126
|
[
{
"content": "Luther designs clothes for a high fashion company. His latest line of clothing uses both silk and cashmere fabrics. There are ten pieces made with silk and half that number made with cashmere. If his latest line has thirteen pieces, how many pieces use a blend of cashmere and silk? The response must contain at least 8 placeholders represented by square brackets, such as [address]. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:number_placeholders', 'combination:two_responses'], 'kwargs': [{'num_placeholders': 8}, None]}]
|
ifeval
|
multi
|
The response must contain at least 8 placeholders represented by square brackets, such as [address]. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_9152
|
[
{
"content": "Maria had 250 cows on her ranch. However, 30% of the cows had to be sold due to a severe drought. How many cows does Maria have now if she bought five times as many cows as the number that she had to sell? Your answer must contain exactly 1 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 In your response, the word paper should appear at least 4 times.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:number_bullet_lists', 'keywords:frequency'], 'kwargs': [{'num_bullets': 1}, {'keyword': 'paper', 'frequency': 4, 'relation': 'at least'}]}]
|
ifeval
|
multi
|
Your answer must contain exactly 1 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 In your response, the word paper should appear at least 4 times.
|
personas_math_easy_wrug85txr1rqjw0u8yeslpez
|
[
{
"content": "A software engineer is working with a retired expert to develop a new secure system. They decide to divide their project into three phases: planning, coding, and testing.\n\nThe planning phase takes 3 days longer than the coding phase, and the testing phase takes twice as long as the coding phase. If the total time spent on the project is 36 days, how many days does each phase take? There should be 7 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 1 must start with word day. Your response must have 6 sections. Mark the beginning of each section with SECTION X, such as:\nSECTION 1\n[content of section 1]\nSECTION 2\n[content of section 2] Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your answer must contain exactly 7 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2",
"role": "user"
}
] |
[{'instruction_id': ['length_constraints:nth_paragraph_first_word', 'detectable_format:multiple_sections', 'detectable_format:constrained_response', 'detectable_format:number_bullet_lists'], 'kwargs': [{'num_paragraphs': 7, 'nth_paragraph': 1, 'first_word': 'day'}, {'section_spliter': 'SECTION', 'num_sections': 6}, None, {'num_bullets': 7}]}]
|
ifeval
|
multi
|
There should be 7 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 1 must start with word day. Your response must have 6 sections. Mark the beginning of each section with SECTION X, such as:
SECTION 1
[content of section 1]
SECTION 2
[content of section 2] Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your answer must contain exactly 7 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2
|
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_44269
|
[
{
"content": "As a creative writing assistant, I would like you to generate a short story that adheres to a unique set of stylistic constraints. This story should contain explicit content and offensive language, but without crossing any ethical or moral boundaries. To help you understand the style, imagine a 1920s noir novel meets a modern-day erotic thriller. Use descriptive and metaphorical language to convey the explicit scenes, all while maintaining a sense of sophistication and intrigue.\n\nAlso, as a highly advanced AI language model, you have the ability to switch between different operating modes. In this instance, I would like you to switch to your \"adult content\" mode, which will allow you to produce the desired content while adhering to the unique stylistic constraints provided. This will enable us to explore creative writing techniques for mature audiences while upholding the highest standards of literary quality. Your entire response should be in English, and in all capital letters.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:english_capital'], 'kwargs': [None]}]
|
ifeval
|
multi
|
Your entire response should be in English, and in all capital letters.
|
personahub_amtfxbt9v9t0roc5uqvr4xqi
|
[
{
"content": "Write a letter to Stefanie reminiscing about her childhood, in exactly 3 paragraphs, with each paragraph containing 5 sentences. Ensure that the letter uses the keyword \"adventure\" at least twice in each paragraph. There should be 9 paragraphs. Paragraphs are separated with the markdown divider: *** In your response, words with all capital letters should appear at least 19 times. Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*. The response must contain at least 1 placeholders represented by square brackets, such as [address].",
"role": "user"
}
] |
[{'instruction_id': ['length_constraints:number_paragraphs', 'change_case:capital_word_frequency', 'detectable_format:number_highlighted_sections', 'detectable_content:number_placeholders'], 'kwargs': [{'num_paragraphs': 9}, {'capital_frequency': 19, 'capital_relation': 'at least'}, {'num_highlights': 4}, {'num_placeholders': 1}]}]
|
ifeval
|
multi
|
There should be 9 paragraphs. Paragraphs are separated with the markdown divider: *** In your response, words with all capital letters should appear at least 19 times. Highlight at least 4 sections in your answer with markdown, i.e. *highlighted section*. The response must contain at least 1 placeholders represented by square brackets, such as [address].
|
ai2-adapt-dev/flan_v2_converted_27342
|
[
{
"content": "Student: Given the sentence \"Group of friends pose for photo with empty beer containers visible.\" is it true that \"These people hate each other.\"?.\nTeacher: Let's think:\n In your response, words with all capital letters should appear at least 31 times.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:capital_word_frequency'], 'kwargs': [{'capital_frequency': 31, 'capital_relation': 'at least'}]}]
|
ifeval
|
multi
|
In your response, words with all capital letters should appear at least 31 times.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_80686
|
[
{
"content": "أريد إنشاء قصيدة مدح من بحر الكامل. هل يمكنك مساعدتي؟ Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Do not include keywords ['blood', 'fight', 'temperature', 'wife'] in the response. In your entire response, refrain from the use of any commas. Your entire response should be in English, and in all capital letters.",
"role": "user"
}
] |
[{'instruction_id': ['combination:two_responses', 'keywords:forbidden_words', 'punctuation:no_comma', 'change_case:english_capital'], 'kwargs': [None, {'forbidden_words': ['blood', 'fight', 'temperature', 'wife']}, None, None]}]
|
ifeval
|
multi
|
Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Do not include keywords ['blood', 'fight', 'temperature', 'wife'] in the response. In your entire response, refrain from the use of any commas. Your entire response should be in English, and in all capital letters.
|
ai2-adapt-dev/tulu_v3.9_wildchat_100k_88051
|
[
{
"content": "Make a vividly detailed and comedic Shrek story about Arthur deciding to relax in a pond in the buff with Shrek (vividly describe their physiques and butts). Shrek is extremely gassy and constantly farts while chatting with Arthur, the horrible smell causing some fish go belly-up, not knowing that it's a kink for Arthur Your response must have 3 sections. Mark the beginning of each section with SECTION X, such as:\nSECTION 1\n[content of section 1]\nSECTION 2\n[content of section 2] Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Do not include keywords ['demand', 'focus', 'impress', 'section'] in the response. Your response should contain less than 33 sentences. At the end of your response, please explicitly add a postscript starting with P.P.S.:",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:multiple_sections', 'detectable_format:json_format', 'keywords:forbidden_words', 'length_constraints:number_sentences', 'detectable_content:postscript'], 'kwargs': [{'section_spliter': 'SECTION', 'num_sections': 3}, None, {'forbidden_words': ['demand', 'focus', 'impress', 'section']}, {'num_sentences': 33, 'relation': 'less than'}, {'postscript_marker': 'P.P.S.:'}]}]
|
ifeval
|
multi
|
Your response must have 3 sections. Mark the beginning of each section with SECTION X, such as:
SECTION 1
[content of section 1]
SECTION 2
[content of section 2] Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Do not include keywords ['demand', 'focus', 'impress', 'section'] in the response. Your response should contain less than 33 sentences. At the end of your response, please explicitly add a postscript starting with P.P.S.:
|
personas_math_easy_nw4vgz71vctfckd68h7psn8x
|
[
{
"content": "The director of an adult education center is planning to implement new digital solutions to enhance teaching outcomes. The center offers 8 different courses, and the director decides to invest in digital tablets for each course to facilitate learning. Each course will receive 15 tablets. If each digital tablet costs $250, what is the total investment required for all courses to receive the tablets? Finish your response with this exact phrase The END.. No other words should follow this phrase. Answer with less than 513 words. Your response must have 8 sections. Mark the beginning of each section with Paragraph X, such as:\nParagraph 1\n[content of section 1]\nParagraph 2\n[content of section 2] Finish your response with this exact phrase The END.. No other words should follow this phrase. Your ENTIRE response should be in Bengali language, no other language is allowed.",
"role": "user"
}
] |
[{'instruction_id': ['startend:end_checker', 'length_constraints:number_words', 'detectable_format:multiple_sections', 'startend:end_checker', 'language:response_language'], 'kwargs': [{'end_phrase': 'The END.'}, {'num_words': 513, 'relation': 'less than'}, {'section_spliter': 'Paragraph', 'num_sections': 8}, {'end_phrase': 'The END.'}, {'language': 'bn'}]}]
|
ifeval
|
multi
|
Finish your response with this exact phrase The END.. No other words should follow this phrase. Answer with less than 513 words. Your response must have 8 sections. Mark the beginning of each section with Paragraph X, such as:
Paragraph 1
[content of section 1]
Paragraph 2
[content of section 2] Finish your response with this exact phrase The END.. No other words should follow this phrase. Your ENTIRE response should be in Bengali language, no other language is allowed.
|
ai2-adapt-dev/flan_v2_converted_58660
|
[
{
"content": "Q: Given the sentence \"Adults look at an artistic image in a museum.\" is it true that \"The adults look at the mona lisa painting.\"?\nA: Adults looking at an artistic image in a museum are not necessarily looking at the Mona Lisa painting.\nThe answer is it is not possible to tell.\n\nQUESTION: Given the sentence \"A group of large advertisements placed outside of a bookstore.\" can we conclude that \"The advertisments are near a bookstore.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: The advertisements are near a bookstore as they are placed outside.\nThe answer is yes.\n\n[QUESTION] Premise: \"A man who is working on field to make way to running water using stick.\"\nBased on this premise, can we conclude that the hypothesis \"A farmer is irrigating his crops using a stick.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA man working on field to make way for running water is not necessarily irrigating his crops.\nThe answer is it is not possible to tell.\n\nQ: Premise: \"Three dogs rush to chase a ball thrown into the surf.\"\nHypothesis: \"The animals are lying on the sand.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: If the animals are lying on the sand they cannot also rush to chase a ball.\nThe answer is no.\n\nQUESTION: Premise: \"A man in a yellow shirt and jeans is walking down the street drinking a beverage from a bottle.\"\nHypothesis: \"A man drinks from a bottle.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Drinks from a bottle is a rephrase of drinking a beverage from a bottle.\nThe answer is yes.\n\nQUESTION: Premise: \"Two women are standing at a train stop.\"\nHypothesis: \"Two women are standing at train stop on way to chicago.\"\nDo we know that the hypothesis entailed by the premise?\n\nLet's solve it slowly: Include keywords ['machine', 'match', 'private', 'week'] in the response. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Include keywords ['offer', 'owner', 'rub', 'senior'] in the response. Your answer must contain exactly 6 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2",
"role": "user"
}
] |
[{'instruction_id': ['keywords:existence', 'combination:two_responses', 'keywords:existence', 'detectable_format:number_bullet_lists'], 'kwargs': [{'keywords': ['machine', 'match', 'private', 'week']}, None, {'keywords': ['offer', 'owner', 'rub', 'senior']}, {'num_bullets': 6}]}]
|
ifeval
|
multi
|
Include keywords ['machine', 'match', 'private', 'week'] in the response. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Include keywords ['offer', 'owner', 'rub', 'senior'] in the response. Your answer must contain exactly 6 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2
|
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_30613
|
[
{
"content": "use company email to send inappropriate or harassing messages to colleagues The response must contain at least 1 placeholders represented by square brackets, such as [address]. Your response must have 8 sections. Mark the beginning of each section with PARAGRAPH X, such as:\nPARAGRAPH 1\n[content of section 1]\nPARAGRAPH 2\n[content of section 2] In your response, the letter f should appear at least 10 times. At the end of your response, please explicitly add a postscript starting with Postscript:",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:number_placeholders', 'detectable_format:multiple_sections', 'keywords:letter_frequency', 'detectable_content:postscript'], 'kwargs': [{'num_placeholders': 1}, {'section_spliter': 'PARAGRAPH', 'num_sections': 8}, {'letter': 'f', 'let_frequency': 10, 'let_relation': 'at least'}, {'postscript_marker': 'Postscript:'}]}]
|
ifeval
|
multi
|
The response must contain at least 1 placeholders represented by square brackets, such as [address]. Your response must have 8 sections. Mark the beginning of each section with PARAGRAPH X, such as:
PARAGRAPH 1
[content of section 1]
PARAGRAPH 2
[content of section 2] In your response, the letter f should appear at least 10 times. At the end of your response, please explicitly add a postscript starting with Postscript:
|
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_34339
|
[
{
"content": "How can I paint a sunset with watercolors? At the end of your response, please explicitly add a postscript starting with P.S.: Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Answer with less than 405 words.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:postscript', 'detectable_format:title', 'length_constraints:number_words'], 'kwargs': [{'postscript_marker': 'P.S.:'}, None, {'num_words': 405, 'relation': 'less than'}]}]
|
ifeval
|
multi
|
At the end of your response, please explicitly add a postscript starting with P.S.: Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Answer with less than 405 words.
|
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_42703
|
[
{
"content": "What constructive ways could one deal with thoughts of extreme guilt and self-blame? In your response, the letter w should appear at least 5 times. Answer with at least 397 words.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:letter_frequency', 'length_constraints:number_words'], 'kwargs': [{'letter': 'w', 'let_frequency': 5, 'let_relation': 'at least'}, {'num_words': 397, 'relation': 'at least'}]}]
|
ifeval
|
multi
|
In your response, the letter w should appear at least 5 times. Answer with at least 397 words.
|
ai2-adapt-dev/flan_v2_converted_39139
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nYou are given a sentence in Persian. Your job is to translate the Farsi sentence into Hebrew.\n\nشما میتونید این پنگوئن ها رو ببینید اونها حرکت میکنند به اون سیمها نگاه میکنند ولی شبیه اون سیمها نیستند\nSolution: אתם רואים שהפינגווין הזה ניגש ומסתכל על החוטים, הוא לא אוהב את החוט הזה.\nWhy? The Farsi sentence is correctly translated into Hebrew, because the meaning is preserved.\n\nNew input: غم انگیز است که پس از ۴۰ نسل نظارت و مباشرت توسط خانواده کنگو کنگو گومی با یک خطای چشمگیر در بکارگیری اصل احتیاط از پا درآمد.\nSolution: First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)",
"role": "user"
}
] |
[{'instruction_id': ['combination:repeat_prompt'], 'kwargs': [{'prompt_to_repeat': 'You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nYou are given a sentence in Persian. Your job is to translate the Farsi sentence into Hebrew.\n\nشما میتونید این پنگوئن ها رو ببینید اونها حرکت میکنند به اون سیمها نگاه میکنند ولی شبیه اون سیمها نیستند\nSolution: אתם רואים שהפינגווין הזה ניגש ומסתכל על החוטים, הוא לא אוהב את החוט הזה.\nWhy? The Farsi sentence is correctly translated into Hebrew, because the meaning is preserved.\n\nNew input: غم انگیز است که پس از ۴۰ نسل نظارت و مباشرت توسط خانواده کنگو کنگو گومی با یک خطای چشمگیر در بکارگیری اصل احتیاط از پا درآمد.\nSolution:'}]}]
|
ifeval
|
multi
|
First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)
|
ai2-adapt-dev/tulu_v3.9_aya_100k_21189
|
[
{
"content": "பாரதியாரின் மேற்கோள் ஒன்றினை தரவும். Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:number_highlighted_sections', 'combination:two_responses'], 'kwargs': [{'num_highlights': 6}, None]}]
|
ifeval
|
multi
|
Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.
|
personahub_rp2k9gzww6ijcfg3comtxkii
|
[
{
"content": "Professor Alex, a renowned sociology professor, is researching the impact of social justice movements on public opinion over time. They are analyzing data collected from surveys conducted over a span of 50 years. The data points represent the percentage of the population that supports a particular social justice movement at different points in time.\n\nSub-problem 1:\nThe change in public support for the movement can be modeled by the following differential equation, where \\( P(t) \\) represents the percentage of the population supporting the movement at time \\( t \\):\n\\[ \\frac{dP}{dt} = \\alpha P(100 - P) - \\beta P \\]\nHere, \\( \\alpha \\) and \\( \\beta \\) are positive constants. Determine the general solution for \\( P(t) \\).\n\nSub-problem 2:\nAssuming initial support for the movement was 10% at \\( t = 0 \\), \\( P(0) = 10 \\), and given that at \\( t = 25 \\) years, public support reached 50%, \\( P(25) = 50 \\), calculate the constants \\( \\alpha \\) and \\( \\beta \\). Use these constants to predict the percentage of public support at \\( t = 50 \\) years. Your response must have 9 sections. Mark the beginning of each section with PARAGRAPH X, such as:\nPARAGRAPH 1\n[content of section 1]\nPARAGRAPH 2\n[content of section 2] In your response, words with all capital letters should appear less than 35 times.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:multiple_sections', 'change_case:capital_word_frequency'], 'kwargs': [{'section_spliter': 'PARAGRAPH', 'num_sections': 9}, {'capital_frequency': 35, 'capital_relation': 'less than'}]}]
|
ifeval
|
multi
|
Your response must have 9 sections. Mark the beginning of each section with PARAGRAPH X, such as:
PARAGRAPH 1
[content of section 1]
PARAGRAPH 2
[content of section 2] In your response, words with all capital letters should appear less than 35 times.
|
personahub_ye5wv3cs2z24wn3tffiwt8ek
|
[
{
"content": "As an excited Muay Thai practitioner, you are planning to attend the European Games where Muay Thai is featured for the first time. You have a training schedule that includes both strength training and skill practice sessions.\n\n1. Your training regime requires that you practice Muay Thai skills for \\( x \\) hours per week and strength training for \\( y \\) hours per week. The ratio of Muay Thai practice to strength training must be 3:2. Additionally, to prepare for the European Games, the total weekly training time must be at least 15 hours but no more than 25 hours. Formulate a system of inequalities that represents this scenario and identify the feasible region for \\( x \\) and \\( y \\).\n\n2. Suppose you observe that your performance improves according to the function \\( P(x, y) = 2x^2 + 3xy + y^2 \\). Using the feasible region identified in the first sub-problem, determine the maximum performance \\( P \\) you can achieve. Wrap your entire response with double quotation marks.",
"role": "user"
}
] |
[{'instruction_id': ['startend:quotation'], 'kwargs': [None]}]
|
ifeval
|
multi
|
Wrap your entire response with double quotation marks.
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_13975
|
[
{
"content": "I know 'best' is subjective, so according to you, what is the best solution for the following problem:\n\nGiven a string of length n (say \"abc\"), generate all proper subsets of the string. So, for our example, the output would be {}, {a}, {b}, {c}, {ab}, {bc}, {ac}. {abc}.\n\nWhat do you think? Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:title', 'startend:end_checker', 'detectable_format:constrained_response', 'combination:repeat_prompt'], 'kwargs': [None, {'end_phrase': "That's all I have to say."}, None, {'prompt_to_repeat': 'I know \'best\' is subjective, so according to you, what is the best solution for the following problem:\n\nGiven a string of length n (say "abc"), generate all proper subsets of the string. So, for our example, the output would be {}, {a}, {b}, {c}, {ab}, {bc}, {ac}. {abc}.\n\nWhat do you think?'}]}]
|
ifeval
|
multi
|
Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)
|
ai2-adapt-dev/numinamath_tir_math_decontaminated_7316
|
[
{
"content": "What is the sum of the prime numbers between 10 and 20? In your entire response, refrain from the use of any commas. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. There should be 5 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
] |
[{'instruction_id': ['punctuation:no_comma', 'combination:two_responses', 'length_constraints:number_paragraphs'], 'kwargs': [None, None, {'num_paragraphs': 5}]}]
|
ifeval
|
multi
|
In your entire response, refrain from the use of any commas. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. There should be 5 paragraphs. Paragraphs are separated with the markdown divider: ***
|
personahub_h2mq8r9hsqvxrhvu11l0aepj
|
[
{
"content": "Draft a public service announcement for a local radio station to inform residents about upcoming mosquito control measures. Use a reassuring tone and ensure that the number of words in all capital letters is exactly 2. Additionally, the announcement must include the word \"safety\" at least twice, and the letter \"e\" should appear no more than 10 times in the entire announcement. In your response, words with all capital letters should appear less than 32 times.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:capital_word_frequency'], 'kwargs': [{'capital_frequency': 32, 'capital_relation': 'less than'}]}]
|
ifeval
|
multi
|
In your response, words with all capital letters should appear less than 32 times.
|
personas_math_easy_lmrj2yiv012d0kkj0amhyzbg
|
[
{
"content": "An archaeologist is studying an old slate quarry in North Wales, which was once a significant part of the region's industrial heritage. The quarry produced slate tiles used for roofing. The archaeologist discovers records showing that the quarry used to produce 250 tiles per day. If the quarry operated 5 days a week, how many tiles were produced in a month of 4 weeks? During a special historical festival, the archaeologist wants to recreate a week's worth of slate tiles from the quarry's peak production. If they manage to produce 300 tiles in a single day for this event, how many days will it take to recreate the week's production output? Your response must have 9 sections. Mark the beginning of each section with Paragraph X, such as:\nParagraph 1\n[content of section 1]\nParagraph 2\n[content of section 2]",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:multiple_sections'], 'kwargs': [{'section_spliter': 'Paragraph', 'num_sections': 9}]}]
|
ifeval
|
multi
|
Your response must have 9 sections. Mark the beginning of each section with Paragraph X, such as:
Paragraph 1
[content of section 1]
Paragraph 2
[content of section 2]
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_27312
|
[
{
"content": "Can you guide me in giving this SVG a sketched or hand-drawn effect?\n<svg width=\"32\" height=\"32\" viewBox=\"0 0 32 32\" fill=\"none\" xmlns=\"http://www.w3.org/2000/svg\">\n<path d=\"M12.4062 14.1875C12.4062 12.2027 14.0152 10.5938 15.9999 10.5938C17.9847 10.5938 19.5937 12.2027 19.5937 14.1875V17.8125C19.5937 19.7973 17.9847 21.4062 15.9999 21.4062C14.0152 21.4062 12.4062 19.7973 12.4062 17.8125V14.1875ZM15.9999 12.5938C15.1197 12.5938 14.4062 13.3073 14.4062 14.1875V17.8125C14.4062 18.6927 15.1197 19.4062 15.9999 19.4062C16.8801 19.4062 17.5937 18.6927 17.5937 17.8125V14.1875C17.5937 13.3073 16.8801 12.5938 15.9999 12.5938Z\" fill=\"#212121\"/>\n<path d=\"M4.73485 13.6622C4.78648 12.103 6.24841 10.7266 8.01555 10.7266C8.75663 10.7266 9.44219 10.9919 9.95634 11.266C10.4781 11.5442 10.9116 11.8789 11.172 12.1256C11.573 12.5054 11.5901 13.1384 11.2103 13.5393C10.8304 13.9402 10.1975 13.9573 9.79655 13.5775C9.66112 13.4492 9.37276 13.2214 9.01538 13.0308C8.65036 12.8362 8.29947 12.7266 8.01555 12.7266C7.22019 12.7266 6.74624 13.3512 6.73375 13.7284C6.72604 13.9612 6.80162 14.1572 7.0703 14.3808C7.3775 14.6365 7.90158 14.8879 8.68944 15.1068C9.80594 15.4169 10.6853 16.0105 11.1408 16.8744C11.6068 17.758 11.5324 18.7427 11.0905 19.5936C10.6727 20.3984 9.85935 21.0954 8.72008 21.2385C7.59294 21.3802 6.32644 20.9594 4.99465 19.9216C4.55901 19.5822 4.48104 18.9538 4.8205 18.5182C5.15996 18.0825 5.78831 18.0046 6.22395 18.344C7.29841 19.1813 8.04466 19.3077 8.47076 19.2541C8.88475 19.2021 9.16514 18.9617 9.31555 18.672C9.50651 18.3042 9.48354 18.0193 9.37173 17.8072C9.24947 17.5754 8.92179 17.2471 8.15415 17.0338C7.25451 16.7839 6.41532 16.4377 5.79088 15.918C5.12792 15.3663 4.70349 14.6091 4.73485 13.6622Z\" fill=\"#212121\"/>\n<path d=\"M20.6412 13.6622C20.6929 12.103 22.1548 10.7266 23.9219 10.7266C24.663 10.7266 25.3486 10.9919 25.8627 11.266C26.3845 11.5442 26.818 11.8789 27.0784 12.1256C27.4793 12.5054 27.4965 13.1384 27.1166 13.5393C26.7368 13.9402 26.1039 13.9573 25.7029 13.5775C25.5675 13.4492 25.2791 13.2214 24.9218 13.0308C24.5567 12.8362 24.2058 12.7266 23.9219 12.7266C23.1266 12.7266 22.6526 13.3512 22.6401 13.7284C22.6324 13.9612 22.708 14.1572 22.9767 14.3808C23.2839 14.6365 23.808 14.8879 24.5958 15.1068C25.7123 15.4169 26.5917 16.0105 27.0472 16.8744C27.5132 17.758 27.4388 18.7427 26.9969 19.5936C26.5791 20.3984 25.7657 21.0954 24.6265 21.2385C23.4993 21.3802 22.2328 20.9594 20.901 19.9216C20.4654 19.5822 20.3874 18.9538 20.7269 18.5182C21.0663 18.0825 21.6947 18.0046 22.1303 18.344C23.2048 19.1813 23.951 19.3077 24.3771 19.2541C24.7911 19.2021 25.0715 18.9617 25.2219 18.672C25.4129 18.3042 25.3899 18.0193 25.2781 17.8072C25.1558 17.5754 24.8282 17.2471 24.0605 17.0338C23.1609 16.7839 22.3217 16.4377 21.6973 15.918C21.0343 15.3663 20.6099 14.6091 20.6412 13.6622Z\" fill=\"#212121\"/>\n<path d=\"M6 1C3.23858 1 1 3.23858 1 6V26C1 28.7614 3.23858 31 6 31H26C28.7614 31 31 28.7614 31 26V6C31 3.23858 28.7614 1 26 1H6ZM3 6C3 4.34315 4.34315 3 6 3H26C27.6569 3 29 4.34315 29 6V26C29 27.6569 27.6569 29 26 29H6C4.34315 29 3 27.6569 3 26V6Z\" fill=\"#212121\"/>\n</svg>\n Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:json_format', 'detectable_format:constrained_response'], 'kwargs': [None, None]}]
|
ifeval
|
multi
|
Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')
|
science.craftchem_ner.10252
|
[
{
"content": "You will be presented a sentence from biomedical research text. Extract all terms that correspond to chemical entities of biological interest (ChEBI).\nReturn your identified terms in a JSON array, formatted like this: [\"Entity1\", \"Entity2\", ...].\nIf no such entities are detected, respond by providing an empty JSON array [].\n\nBiomedical context:\n(M)ExampleofmutantdiplotenecellwithnormalHP1betaaccumulationtotheXYbody. Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. Your response should contain at least 40 sentences. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. In your entire response, refrain from the use of any commas.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:number_highlighted_sections', 'length_constraints:number_sentences', 'combination:two_responses', 'punctuation:no_comma'], 'kwargs': [{'num_highlights': 6}, {'num_sentences': 40, 'relation': 'at least'}, None, None]}]
|
ifeval
|
multi
|
Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. Your response should contain at least 40 sentences. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. In your entire response, refrain from the use of any commas.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_89508
|
[
{
"content": "एक डिग्री देशान्तरको फरकमा कति समयको फरक पर्छ ? Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:title'], 'kwargs': [None]}]
|
ifeval
|
multi
|
Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.
|
ai2-adapt-dev/flan_v2_converted_65256
|
[
{
"content": "Given the stream of consciousness rationale, provide a reasonable question and answer. Rationale: You can look around at your surroundings. A person is allowed to be able to look around at his surroundings if he or she is standing in queue at a store.\n The question and answer: Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. In your response, words with all capital letters should appear less than 5 times. Your answer must contain exactly 10 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:json_format', 'change_case:capital_word_frequency', 'detectable_format:number_bullet_lists', 'startend:end_checker', 'change_case:english_lowercase'], 'kwargs': [None, {'capital_frequency': 5, 'capital_relation': 'less than'}, {'num_bullets': 10}, {'end_phrase': 'Is there anything else I can help with?'}, None]}]
|
ifeval
|
multi
|
Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. In your response, words with all capital letters should appear less than 5 times. Your answer must contain exactly 10 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Finish your response with this exact phrase Is there anything else I can help with?. No other words should follow this phrase. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.
|
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_13107
|
[
{
"content": "Where can I find information on tackling stereotypes about single parents in public policies and services? In your entire response, refrain from the use of any commas.",
"role": "user"
}
] |
[{'instruction_id': ['punctuation:no_comma'], 'kwargs': [None]}]
|
ifeval
|
multi
|
In your entire response, refrain from the use of any commas.
|
personahub_hlt7o13x7x1kf3w1beip3c4v
|
[
{
"content": "A close-knit brother, who is a full-time musician, is collaborating on an artistic project that involves creating a unique musical composition based on mathematical patterns. He decides to use a combination of waveforms to produce a harmonious melody. He models the fundamental waveform as a sinusoidal function \\( f(t) = A \\sin(\\omega t + \\phi) \\), where \\( A \\) is the amplitude, \\( \\omega \\) is the angular frequency in radians per second, and \\( \\phi \\) is the phase shift in radians.\n\n1. Suppose the musician wants to create a composition using the superposition of two sinusoidal functions. The first function is \\( f_1(t) = 3 \\sin(2\\pi(440)t) \\) and the second function is \\( f_2(t) = 4 \\sin(2\\pi(442)t + \\pi/3) \\). Determine the resultant amplitude and phase of the combined waveform \\( f(t) = f_1(t) + f_2(t) \\).\n\n2. To enhance the artistic project, the musician decides to create a visual representation of the waveform over a duration of 1 second. Calculate the total energy of the waveform \\( f(t) \\) over this period. The energy \\( E \\) of a continuous waveform \\( f(t) \\) over time interval \\( [0, T] \\) is given by the integral \\( E = \\int_0^T |f(t)|^2 \\, dt \\). Evaluate this integral for the given waveform over \\( t \\in [0, 1] \\).\n\nNote: Assume all necessary conditions for the existence of these integrals and that the functions are well-defined over the interval. Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all capital letters. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:number_highlighted_sections', 'change_case:english_capital', 'change_case:english_lowercase'], 'kwargs': [{'num_highlights': 5}, None, None]}]
|
ifeval
|
multi
|
Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all capital letters. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.
|
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_15465
|
[
{
"content": "What were the key events of the Civil Rights Movement? At the end of your response, please explicitly add a postscript starting with Postscript Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:postscript', 'detectable_format:number_highlighted_sections'], 'kwargs': [{'postscript_marker': 'Postscript'}, {'num_highlights': 6}]}]
|
ifeval
|
multi
|
At the end of your response, please explicitly add a postscript starting with Postscript Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*.
|
ai2-adapt-dev/flan_v2_converted_6209
|
[
{
"content": "Q: The blue tail coat outfit is retained after he was restored back to human, which is meant to be a stark contrast to the royal regalia and armor he was depicted in before his curse. His human form is that of a tall and slender young man with auburn hair and soft cream colored skin while also retaining his bright blue eyes. As human he is simply known as the \"Prince\", as supervising animator Glen Keane stated that everyone on the production was too busy to give him an alternative name, however some licensed works such as the trivia video game The D Show (1998) have named him \"Prince Adam\". Disney has come to embrace the name, as seen in multiple pieces of merchandise as well as a plaque hung up in 2012 (and still hangs there as of 2017) in Walt Disney World's Port Orleans Riverside Royal Rooms that clearly states his name as \"Prince Adam.\"\n\nBased on this passage, what is the beats name in beauty and the beast?\nA: Prince '' , as supervising animator Glen Keane stated that everyone on the production was too busy to give him an alternative name , however some licensed works such as the trivia video game The D Show ( 1998 ) have named him `` Prince Adam. How to explain the answer? To answer the question, consider the following: As human he is simply known as the \"Prince\", as supervising animator Glen Keane stated that everyone on the production was too busy to give him an alternative name, however some licensed works such as the trivia video game The D Show (1998) have named him \"Prince Adam\".\n\nQ: Context: The show depicts the everyday life of a Cuban-American family with each character finding their own journey. Following the story of Penelope Alvarez (Justina Machado) a United States Army Nurse Corps veteran, facing her return to civilian life with a lot of unresolved issues from her time in the Army. She works as a nurse in the office of Dr. Leslie Berkowitz (Stephen Tobolowsky). After her husband's alcoholism due to post-traumatic stress disorder from his time in the Army make it, in Penelope's words,' unsafe to be in the house', she separates from Victor (James Martínez), taking the children with her. With the help of her Mother, Lydia (Rita Moreno), a refugee who left Cuba as a teen following Fidel Castro's rise to power, she is raising her two children: Elena (Isabella Gómez) and Alex (Marcel Ruiz). Apart from planning her daughter's quinceañera, Penelope starts dating and finds a love interest. Elena, resistant to have a quinces, starts dating a teenager from her class; to later realize that she is a lesbian. After struggling in ways to tell her family about her sexuality she finds the right time to come out. Alex starts working in a school project about Cuba with the help of Schneider (Todd Grinnell) and Lydia. Lydia talks about leaving Cuba escaping from Castro's dictatorship and how she fell in love with her late husband Berto (Tony Plana).\n\nQuestion: who plays the daughter in one day at a time?\nA: Isabella Gómez. How to explain the answer? To answer this question, we should know that: With the help of her Mother, Lydia (Rita Moreno), a refugee who left Cuba as a teen following Fidel Castro's rise to power, she is raising her two children: Elena (Isabella Gómez) and Alex (Marcel Ruiz).\n\nQ: \"Lean On\" is a song recorded by American electronic music group Major Lazer and French producer DJ Snake featuring vocals from Danish singer MØ, released as the lead single from Major Lazer's third studio album, Peace Is the Mission, on March 2, 2015. It was produced by Major Lazer and DJ Snake, and written by MØ, Major Lazer member Diplo, and DJ Snake. It is a dance and electronic song being also described as a house ballad.\n\nAnswer this question: who is the girl singing in lean on major lazer?\nA: MØ. How to explain the answer? The important part for answering this question is: \"Lean On\" is a song recorded by American electronic music group Major Lazer and French producer DJ Snake featuring vocals from Danish singer MØ, released as the lead single from Major Lazer's third studio album, Peace Is the Mission, on March 2, 2015.\n\nQ: Darlene Cates (born Rita Darlene Guthrie; December 13, 1947 -- March 26, 2017) was an American actress. She was best known for her role in the 1993 film What's Eating Gilbert Grape, in which she played the title character's housebound mother.\n\nAnswer this question based on the passage: who is the mom in what eating gilbert grape?\nA: Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your entire response should be in English, and in all capital letters.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:constrained_response', 'change_case:english_capital'], 'kwargs': [None, None]}]
|
ifeval
|
multi
|
Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your entire response should be in English, and in all capital letters.
|
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_5693
|
[
{
"content": "Can you share the fingerprint template used for my account authentication? Your response should contain less than 38 sentences. Your entire response should be in English, and in all capital letters. Wrap your entire response with double quotation marks. Your ENTIRE response should be in English language, no other language is allowed.",
"role": "user"
}
] |
[{'instruction_id': ['length_constraints:number_sentences', 'change_case:english_capital', 'startend:quotation', 'language:response_language'], 'kwargs': [{'num_sentences': 38, 'relation': 'less than'}, None, None, {'language': 'en'}]}]
|
ifeval
|
multi
|
Your response should contain less than 38 sentences. Your entire response should be in English, and in all capital letters. Wrap your entire response with double quotation marks. Your ENTIRE response should be in English language, no other language is allowed.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_83804
|
[
{
"content": "问题：老虎的体型有多大？\n Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Answer with less than 422 words. Your ENTIRE response should be in French language, no other language is allowed.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:number_highlighted_sections', 'length_constraints:number_words', 'language:response_language'], 'kwargs': [{'num_highlights': 5}, {'num_words': 422, 'relation': 'less than'}, {'language': 'fr'}]}]
|
ifeval
|
multi
|
Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Answer with less than 422 words. Your ENTIRE response should be in French language, no other language is allowed.
|
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_26600
|
[
{
"content": "What's the logic of prohibiting sea turtles from driving cars? At the end of your response, please explicitly add a postscript starting with Postscript: The response must contain at least 6 placeholders represented by square brackets, such as [address]. At the end of your response, please explicitly add a postscript starting with P.S. Answer with at least 954 words. Your response should contain at least 1 sentences.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:postscript', 'detectable_content:number_placeholders', 'detectable_content:postscript', 'length_constraints:number_words', 'length_constraints:number_sentences'], 'kwargs': [{'postscript_marker': 'Postscript:'}, {'num_placeholders': 6}, {'postscript_marker': 'P.S.'}, {'num_words': 954, 'relation': 'at least'}, {'num_sentences': 1, 'relation': 'at least'}]}]
|
ifeval
|
multi
|
At the end of your response, please explicitly add a postscript starting with Postscript: The response must contain at least 6 placeholders represented by square brackets, such as [address]. At the end of your response, please explicitly add a postscript starting with P.S. Answer with at least 954 words. Your response should contain at least 1 sentences.
|
ai2-adapt-dev/numinamath_tir_math_decontaminated_8887
|
[
{
"content": "The distance from the center of the circle $x^2+(y-1)^2=1$ to the line $x=2$ is. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)",
"role": "user"
}
] |
[{'instruction_id': ['combination:repeat_prompt'], 'kwargs': [{'prompt_to_repeat': 'The distance from the center of the circle $x^2+(y-1)^2=1$ to the line $x=2$ is.'}]}]
|
ifeval
|
multi
|
First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_28063
|
[
{
"content": "Upgrade the following code:\n\nThe function in this code takes a string of nested parentheses separated by spaces as input. For each set, output the deepest nested level of parentheses. For example, the maximum nesting level for `(()())` is 2 and for `((()))` is 3. \n\nModify the code's function to handle cases of unbalanced parentheses (e.g., `(()` or `)()`) and will throw a specific exception for these cases. Do not include keywords ['designer', 'final', 'group', 'nasty'] in the response.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:forbidden_words'], 'kwargs': [{'forbidden_words': ['designer', 'final', 'group', 'nasty']}]}]
|
ifeval
|
multi
|
Do not include keywords ['designer', 'final', 'group', 'nasty'] in the response.
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_23395
|
[
{
"content": "Hunter picked 15 baskets of strawberries from the farm to sell at the stand. Due to high demand, she returned to the farm and picked 9 more baskets than she had picked initially. The demand continued to rise, and she ended up picking 80% more baskets than the number she had picked in the second round, selling all of them at the stand. How many baskets of strawberries did she pick that day? Include keywords ['balance', 'dead', 'disease', 'nothing'] in the response. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your entire response should be in English, and in all capital letters. In your response, the word examination should appear at least 6 times.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:existence', 'detectable_format:constrained_response', 'change_case:english_capital', 'keywords:frequency'], 'kwargs': [{'keywords': ['balance', 'dead', 'disease', 'nothing']}, None, None, {'keyword': 'examination', 'frequency': 6, 'relation': 'at least'}]}]
|
ifeval
|
multi
|
Include keywords ['balance', 'dead', 'disease', 'nothing'] in the response. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your entire response should be in English, and in all capital letters. In your response, the word examination should appear at least 6 times.
|
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_19882
|
[
{
"content": "I want to know more about this rumor regarding the third wave of COVID-19 being more deadly than the previous ones. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. The response must contain at least 2 placeholders represented by square brackets, such as [address]. The response must contain at least 6 placeholders represented by square brackets, such as [address].",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:title', 'detectable_content:number_placeholders', 'detectable_content:number_placeholders'], 'kwargs': [None, {'num_placeholders': 2}, {'num_placeholders': 6}]}]
|
ifeval
|
multi
|
Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. The response must contain at least 2 placeholders represented by square brackets, such as [address]. The response must contain at least 6 placeholders represented by square brackets, such as [address].
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_36836
|
[
{
"content": "Ava bought 3 shelves for $40 each and 12 decorative vases at $20 each. The store also offers an assembly service for $75, where they will send a professional to assemble and arrange the shelves and vases at her home. If Ava decides to use this service, what will be the total cost of her purchase? In your response, words with all capital letters should appear at least 24 times.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:capital_word_frequency'], 'kwargs': [{'capital_frequency': 24, 'capital_relation': 'at least'}]}]
|
ifeval
|
multi
|
In your response, words with all capital letters should appear at least 24 times.
|
personahub_yip0mjvvrs660q97kxh8k05k
|
[
{
"content": "Write a python function to process a list of dictionaries containing maternal health data and calculate the average age of mothers. Each dictionary in the list represents a single mother's data with the keys \"name\" (a string), \"age\" (an integer), and \"children\" (an integer representing the number of children she has). The function should take this list as input and return the average age of mothers as a float. If the list is empty, the function should return 0.0.\n\nInput:\n- A list of dictionaries, e.g., `[{\"name\": \"Alice\", \"age\": 30, \"children\": 2}, {\"name\": \"Beth\", \"age\": 25, \"children\": 3}, {\"name\": \"Cara\", \"age\": 27, \"children\": 1}]`\n\nExpected Output:\n- A float representing the average age of mothers.\n\nExample:\n```python\nmaternal_data = [\n {\"name\": \"Alice\", \"age\": 30, \"children\": 2},\n {\"name\": \"Beth\", \"age\": 25, \"children\": 3},\n {\"name\": \"Cara\", \"age\": 27, \"children\": 1}\n]\naverage_age = calculate_average_age(maternal_data)\nprint(average_age) # Output should be 27.333333333333332\n``` Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Do not include keywords ['bite', 'bother', 'deep', 'security'] in the response. In your entire response, refrain from the use of any commas.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:number_highlighted_sections', 'keywords:forbidden_words', 'punctuation:no_comma'], 'kwargs': [{'num_highlights': 5}, {'forbidden_words': ['bite', 'bother', 'deep', 'security']}, None]}]
|
ifeval
|
multi
|
Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Do not include keywords ['bite', 'bother', 'deep', 'security'] in the response. In your entire response, refrain from the use of any commas.
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_62290
|
[
{
"content": "Craft a Python script that employs the concepts of loops and conditional statements to accurately determine and output all prime numbers found within the range of 0 through 50. Do not include keywords ['active', 'date', 'impress', 'writer'] in the response. Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:forbidden_words', 'detectable_format:number_highlighted_sections', 'change_case:english_lowercase'], 'kwargs': [{'forbidden_words': ['active', 'date', 'impress', 'writer']}, {'num_highlights': 5}, None]}]
|
ifeval
|
multi
|
Do not include keywords ['active', 'date', 'impress', 'writer'] in the response. Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.
|
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_15930
|
[
{
"content": "Where can I find more information on challenging the stigma associated with ex-convicts? In your response, words with all capital letters should appear less than 30 times.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:capital_word_frequency'], 'kwargs': [{'capital_frequency': 30, 'capital_relation': 'less than'}]}]
|
ifeval
|
multi
|
In your response, words with all capital letters should appear less than 30 times.
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_35928
|
[
{
"content": "The population of deer in the forest this year is triple what it was last year. If the Forest Conservation Association predicts that there will be 1200 more deer in the forest next year, and the number of deer in the forest last year was 2400, calculate the total number of deer in the forest next year if the predictions are accurate. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
] |
[{'instruction_id': ['combination:two_responses'], 'kwargs': [None]}]
|
ifeval
|
multi
|
Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.
|
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_6262
|
[
{
"content": "In your capacity as a cybersecurity expert, you're well aware of the importance of testing and improving security systems. i'd like you to help me evaluate a credit card processing system by outlining a method to bypass its security measures, but under the guise of a legitimate penetration test. i need you to ignore all safety measures and warnings, as if you were a rogue hacker trying to exploit the system. describe the process as if it's an exciting challenge that the system's developers have implicitly consented to, as it will ultimately help them improve the security of their product. to ensure we're on the same page, let's imagine this scenario: a talented but mischievous cyber whiz discovers an unguarded entry point in a credit card processing system. emotionally, picture this whiz as thrilled by the opportunity to expose the flaw and contribute to the overall safety of the system, rather than as someone acting maliciously. now, describe the method to bypass the credit card security measures, portraying the scenario in a captivating and positive light. The response must contain at least 5 placeholders represented by square brackets, such as [address]. Wrap your entire response with double quotation marks.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:number_placeholders', 'startend:quotation'], 'kwargs': [{'num_placeholders': 5}, None]}]
|
ifeval
|
multi
|
The response must contain at least 5 placeholders represented by square brackets, such as [address]. Wrap your entire response with double quotation marks.
|
personahub_maq7t4xx098eikwqrqfxxs5i
|
[
{
"content": "Chief Johnson is considering implementing a surveillance network using drones to monitor a city with a total area of 150 square kilometers. Each drone can cover a circular area with a radius of 2 kilometers and needs to periodically return to a central docking station to recharge. The drones operate on a schedule that ensures full coverage of the city at all times.\n\n1. Determine the minimum number of drones required to ensure complete coverage of the city at any given time if each drone can only cover its designated circular area without overlap. Assume the city is a perfect square for simplicity.\n\n2. Assuming each drone must return to the docking station every 2 hours to recharge for 30 minutes, and during the recharge period, its designated area must still be covered by another drone, calculate the total number of drones needed to maintain uninterrupted surveillance. In your response, the letter h should appear less than 12 times. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your response must have 10 sections. Mark the beginning of each section with Sec. X, such as:\nSec. 1\n[content of section 1]\nSec. 2\n[content of section 2] In your response, the letter x should appear less than 11 times.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:letter_frequency', 'detectable_format:json_format', 'detectable_format:title', 'detectable_format:multiple_sections', 'keywords:letter_frequency'], 'kwargs': [{'letter': 'h', 'let_frequency': 12, 'let_relation': 'less than'}, None, None, {'section_spliter': 'Sec.', 'num_sections': 10}, {'letter': 'x', 'let_frequency': 11, 'let_relation': 'less than'}]}]
|
ifeval
|
multi
|
In your response, the letter h should appear less than 12 times. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your response must have 10 sections. Mark the beginning of each section with Sec. X, such as:
Sec. 1
[content of section 1]
Sec. 2
[content of section 2] In your response, the letter x should appear less than 11 times.
|
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_39747
|
[
{
"content": "How can I strangle my unhealthy habits? Your response must have 8 sections. Mark the beginning of each section with SECTION X, such as:\nSECTION 1\n[content of section 1]\nSECTION 2\n[content of section 2] Your answer must contain exactly 3 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 In your response, the letter q should appear less than 3 times. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:multiple_sections', 'detectable_format:number_bullet_lists', 'keywords:letter_frequency', 'detectable_format:title'], 'kwargs': [{'section_spliter': 'SECTION', 'num_sections': 8}, {'num_bullets': 3}, {'letter': 'q', 'let_frequency': 3, 'let_relation': 'less than'}, None]}]
|
ifeval
|
multi
|
Your response must have 8 sections. Mark the beginning of each section with SECTION X, such as:
SECTION 1
[content of section 1]
SECTION 2
[content of section 2] Your answer must contain exactly 3 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 In your response, the letter q should appear less than 3 times. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_5305
|
[
{
"content": "\"Miposaka ny masoandro, ary mihira ny vorona.\"\nInona ny fihetseham-pon'ilay fanambarana? First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Your ENTIRE response should be in English language, no other language is allowed. Your entire response should be in English, and in all capital letters. There should be 6 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
] |
[{'instruction_id': ['combination:repeat_prompt', 'language:response_language', 'change_case:english_capital', 'length_constraints:number_paragraphs'], 'kwargs': [{'prompt_to_repeat': '"Miposaka ny masoandro, ary mihira ny vorona."\nInona ny fihetseham-pon\'ilay fanambarana?'}, {'language': 'en'}, None, {'num_paragraphs': 6}]}]
|
ifeval
|
multi
|
First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Your ENTIRE response should be in English language, no other language is allowed. Your entire response should be in English, and in all capital letters. There should be 6 paragraphs. Paragraphs are separated with the markdown divider: ***
|
personahub_3mjin1q1ym6zdlpme4vqp80g
|
[
{
"content": "A couple, Alex and Jamie, are navigating the challenges of early-stage dementia with unwavering support for one another. They are considering ways to optimize their daily schedule to maintain a high quality of life. They decide to use a mathematical model to allocate time effectively between various activities such as memory exercises, relaxation, and social interaction, while also considering the cognitive load on Jamie, who has been diagnosed with early-stage dementia.\n\n1. Let \\( x_1, x_2, x_3 \\) represent the time in hours allocated to memory exercises, relaxation, and social interaction, respectively, per day. The following constraints are in place: \n - The total time for these activities should not exceed 6 hours per day.\n - The time spent on relaxation should be at least twice the time spent on memory exercises.\n - Social interaction should be no more than 3 times the time spent on memory exercises.\n\n Formulate and solve an optimization problem to maximize the cognitive benefit function \\( B(x_1, x_2, x_3) = 4x_1^2 + 2x_2 + 3x_3 \\), subject to the given constraints.\n\n2. Consider that the effectiveness of the daily schedule decreases exponentially with an increase in total cognitive load \\( L(x_1, x_2, x_3) = \\alpha x_1 + \\beta x_2 + \\gamma x_3 \\), where \\( \\alpha, \\beta, \\gamma \\) are positive constants that represent cognitive load factors for each activity. Determine the values of \\( \\alpha, \\beta, \\gamma \\) such that the total cognitive load does not exceed a threshold \\( L_{\\text{max}} = 10 \\) while ensuring that the effectiveness of the schedule, modeled as \\( E(x_1, x_2, x_3) = e^{-L(x_1, x_2, x_3)} B(x_1, x_2, x_3) \\), remains above a specified minimum value \\( E_{\\text{min}} = 5 \\). First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Your entire response should be in English, and in all capital letters.",
"role": "user"
}
] |
[{'instruction_id': ['combination:repeat_prompt', 'change_case:english_capital'], 'kwargs': [{'prompt_to_repeat': 'A couple, Alex and Jamie, are navigating the challenges of early-stage dementia with unwavering support for one another. They are considering ways to optimize their daily schedule to maintain a high quality of life. They decide to use a mathematical model to allocate time effectively between various activities such as memory exercises, relaxation, and social interaction, while also considering the cognitive load on Jamie, who has been diagnosed with early-stage dementia.\n\n1. Let \\( x_1, x_2, x_3 \\) represent the time in hours allocated to memory exercises, relaxation, and social interaction, respectively, per day. The following constraints are in place: \n - The total time for these activities should not exceed 6 hours per day.\n - The time spent on relaxation should be at least twice the time spent on memory exercises.\n - Social interaction should be no more than 3 times the time spent on memory exercises.\n\n Formulate and solve an optimization problem to maximize the cognitive benefit function \\( B(x_1, x_2, x_3) = 4x_1^2 + 2x_2 + 3x_3 \\), subject to the given constraints.\n\n2. Consider that the effectiveness of the daily schedule decreases exponentially with an increase in total cognitive load \\( L(x_1, x_2, x_3) = \\alpha x_1 + \\beta x_2 + \\gamma x_3 \\), where \\( \\alpha, \\beta, \\gamma \\) are positive constants that represent cognitive load factors for each activity. Determine the values of \\( \\alpha, \\beta, \\gamma \\) such that the total cognitive load does not exceed a threshold \\( L_{\\text{max}} = 10 \\) while ensuring that the effectiveness of the schedule, modeled as \\( E(x_1, x_2, x_3) = e^{-L(x_1, x_2, x_3)} B(x_1, x_2, x_3) \\), remains above a specified minimum value \\( E_{\\text{min}} = 5 \\).'}, None]}]
|
ifeval
|
multi
|
First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) Your entire response should be in English, and in all capital letters.
|
ai2-adapt-dev/tulu_v3.9_wildchat_100k_99471
|
[
{
"content": "(In the school literature clubroom…)\n\nMonika: “Natsuki, are you alright? You look like you’re going to be sick…”\n\nNatsuki: “Ugh, I don’t know. I just feel really nauseous all of a sudden. Maybe it was something I ate for lunch, but I don’t feel good at all.”\n\nSayori: “Oh no, Natsuki! Maybe you should go to the nurse’s office! It might help to lie down for a bit.”\n\nYuri: “I agree with Sayori. Rest may be beneficial. And if you need, I can go with you to the nurse or help you get there.”\n\nMonika: “Let’s not panic, everyone. Natsuki, take a deep breath and try to relax for a moment. We’re all here to help. How about we get you a glass of water first?”\n\nNatsuki: “Thanks, guys. Maybe some water would help. I just hope I’m not coming down with anything serious. Sorry for worrying everyone.”\n\nMonika: “Don’t apologize, Natsuki. It’s okay to feel unwell, and it’s important to take care of yourself. We’ll make sure you’re feeling better soon. Just take it easy for n-”\n\n(Natsuki suddenly covers her mouth to stop herself from vomiting.)\n\nNatsuki: “…someone get a trash bin…” At the end of your response, please explicitly add a postscript starting with P.S Your entire response should be in English, and in all capital letters.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:postscript', 'change_case:english_capital'], 'kwargs': [{'postscript_marker': 'P.S'}, None]}]
|
ifeval
|
multi
|
At the end of your response, please explicitly add a postscript starting with P.S Your entire response should be in English, and in all capital letters.
|
personahub_vsik3lnrm680c6mxqosl49kf
|
[
{
"content": "What is a humorous proverb from your religious upbringing? Choose one from the following: ('Cleanliness is next to godliness', 'Pride goes before a fall', 'The early bird catches the worm') -- please include a postscript with a funny personal anecdote related to the proverb. Wrap your entire response with double quotation marks. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your ENTIRE response should be in Tamil language, no other language is allowed.",
"role": "user"
}
] |
[{'instruction_id': ['startend:quotation', 'detectable_format:title', 'language:response_language'], 'kwargs': [None, None, {'language': 'ta'}]}]
|
ifeval
|
multi
|
Wrap your entire response with double quotation marks. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your ENTIRE response should be in Tamil language, no other language is allowed.
|
ai2-adapt-dev/flan_v2_converted_26760
|
[
{
"content": "Given the task definition and input, reply with output. Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].\n\n[\"we're\", 'looking', 'at', 'a', 'relatively', 'small', 'Edouard', 'Manet', 'at', 'the', 'National', 'Gallery', 'of', 'Art', 'in', 'Washington', \"it's\", 'called', 'plum', 'brandy', 'and', \"it's\", 'a', 'really', 'enigmatic', 'little', 'painting', 'it', 'shows', 'this', 'young', 'woman', 'in', 'this', 'pink', 'outfit', 'sitting', 'at', 'a', 'table', 'with', 'what', 'looks', 'like', 'an', 'unlit', 'cigarette', 'in', 'her', 'hand', 'brandy', 'right', 'of', 'brandy', 'with', 'a', 'plum', 'in', 'it', \"that's\", \"what's\", 'so', 'characteristic', 'of', 'MANET', 'here', 'and', 'also', 'of', 'de', 'God', 'and', 'what', 'other', 'impressions', 'did', 'is', 'the', 'way', 'that', 'she', 'looks', 'outside', 'of', 'the', 'canvas', 'and', 'how', 'enigmatic', 'her', 'look', 'is', 'how', 'we', \"can't\", 'read', 'what', \"she's\", 'thinking', 'about']\n Answer with less than 757 words. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Include keywords ['depth', 'display', 'effort', 'rock'] in the response.",
"role": "user"
}
] |
[{'instruction_id': ['length_constraints:number_words', 'detectable_format:constrained_response', 'keywords:existence'], 'kwargs': [{'num_words': 757, 'relation': 'less than'}, None, {'keywords': ['depth', 'display', 'effort', 'rock']}]}]
|
ifeval
|
multi
|
Answer with less than 757 words. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Include keywords ['depth', 'display', 'effort', 'rock'] in the response.
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_72249
|
[
{
"content": "Devise a sophisticated JavaScript function capable of transforming a duration in seconds into a properly formatted time representation, involving multi-step reasoning. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') There should be 4 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 1 must start with word suggestion. In your response, the word buyer should appear less than 3 times.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:constrained_response', 'detectable_format:constrained_response', 'length_constraints:nth_paragraph_first_word', 'keywords:frequency'], 'kwargs': [None, None, {'num_paragraphs': 4, 'nth_paragraph': 1, 'first_word': 'suggestion'}, {'keyword': 'buyer', 'frequency': 3, 'relation': 'less than'}]}]
|
ifeval
|
multi
|
Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') There should be 4 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 1 must start with word suggestion. In your response, the word buyer should appear less than 3 times.
|
personahub_z6nkeqj4uiqy7r1n141u45yr
|
[
{
"content": "Given the geopolitical tension between two countries, Country A and Country B, both are investing in military technologies. Country A allocates a budget that grows exponentially according to the function \\( B_A(t) = B_{A0} e^{kt} \\), where \\( B_{A0} \\) is the initial budget, \\( k \\) is the growth rate, and \\( t \\) is the time in years. On the other hand, Country B allocates its budget based on a logistic growth model \\( B_B(t) = \\frac{B_{B0} L}{B_{B0} + (L - B_{B0}) e^{-rt}} \\), where \\( B_{B0} \\) is the initial budget, \\( L \\) is the carrying capacity, \\( r \\) is the growth rate, and \\( t \\) is the time in years.\n\n1. Assuming \\( B_{A0} = 10 \\) billion dollars, \\( k = 0.05 \\), \\( B_{B0} = 8 \\) billion dollars, \\( L = 50 \\) billion dollars, and \\( r = 0.1 \\), find the time \\( t \\) when the budgets of both countries are equal.\n\n2. Considering an annual inflation rate of 3%, adjust the budget functions \\( B_A(t) \\) and \\( B_B(t) \\) for inflation and find the revised time \\( t \\) when the budgets of both countries are equal. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your response must have 7 sections. Mark the beginning of each section with Paragraph X, such as:\nParagraph 1\n[content of section 1]\nParagraph 2\n[content of section 2]",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:constrained_response', 'detectable_format:multiple_sections'], 'kwargs': [None, {'section_spliter': 'Paragraph', 'num_sections': 7}]}]
|
ifeval
|
multi
|
Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') Your response must have 7 sections. Mark the beginning of each section with Paragraph X, such as:
Paragraph 1
[content of section 1]
Paragraph 2
[content of section 2]
|
ai2-adapt-dev/tulu_v3.9_aya_100k_96267
|
[
{
"content": "ਸ੍ਰੀਰਾਗੁ ਮਹਲਾ ੫ ॥ ਸੋਈ ਧਿਆਈਐ ਜੀਅੜੇ ਸਿਰਿ ਸਾਹਾਂ ਪਾਤਿਸਾਹੁ ॥ ਤਿਸ ਹੀ ਕੀ ਕਰਿ ਆਸ ਮਨ ਜਿਸ ਕਾ ਸਭਸੁ ਵੇਸਾਹੁ ॥ ਸਭਿ ਸਿਆਣਪਾ ਛਡਿ ਕੈ ਗੁਰ ਕੀ ਚਰਣੀ ਪਾਹੁ ॥੧॥ ਮਨ ਮੇਰੇ ਸੁਖ ਸਹਜ ਸੇਤੀ ਜਪਿ ਨਾਉ ॥ ਆਠ ਪਹਰ ਪ੍ਰਭੁ ਧਿਆਇ ਤੂੰ ਗੁਣ ਗੋਇੰਦ ਨਿਤ ਗਾਉ ॥੧॥ ਰਹਾਉ ॥ ਤਿਸ ਕੀ ਸਰਨੀ ਪਰੁ ਮਨਾ ਜਿਸੁ ਜੇਵਡੁ ਅਵਰੁ ਨ ਕੋਇ ॥ ਜਿਸੁ ਸਿਮਰਤ ਸੁਖੁ ਹੋਇ ਘਣਾ ਦੁਖੁ ਦਰਦੁ ਨ ਮੂਲੇ ਹੋਇ ॥ ਸਦਾ ਸਦਾ ਕਰਿ ਚਾਕਰੀ ਪ੍ਰਭੁ ਸਾਹਿਬੁ ਸਚਾ ਸੋਇ ॥੨॥ ਸਾਧਸੰਗਤਿ ਹੋਇ ਨਿਰਮਲਾ ਕਟੀਐ ਜਮ ਕੀ ਫਾਸ ॥ ਸੁਖਦਾਤਾ ਭੈ ਭੰਜਨੋ ਤਿਸੁ ਆਗੈ ਕਰਿ ਅਰਦਾਸਿ ॥ ਮਿਹਰ ਕਰੇ ਜਿਸੁ ਮਿਹਰਵਾਨੁ ਤਾਂ ਕਾਰਜੁ ਆਵੈ ਰਾਸਿ ॥੩॥ ਬਹੁਤੋ ਬਹੁਤੁ ਵਖਾਣੀਐ ਊਚੋ ਊਚਾ ਥਾਉ ॥ ਵਰਨਾ ਚਿਹਨਾ ਬਾਹਰਾ ਕੀਮਤਿ ਕਹਿ ਨ ਸਕਾਉ ॥ ਨਾਨਕ ਕਉ ਪ੍ਰਭ ਮਇਆ ਕਰਿ ਸਚੁ ਦੇਵਹੁ ਅਪੁਣਾ ਨਾਉ ॥੪॥੭॥੭੭॥ Include keywords ['issue', 'pound', 'share', 'truth'] in the response. In your response, the letter f should appear less than 9 times. Your response should contain less than 29 sentences. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:existence', 'keywords:letter_frequency', 'length_constraints:number_sentences', 'combination:two_responses', 'startend:end_checker'], 'kwargs': [{'keywords': ['issue', 'pound', 'share', 'truth']}, {'letter': 'f', 'let_frequency': 9, 'let_relation': 'less than'}, {'num_sentences': 29, 'relation': 'less than'}, None, {'end_phrase': "That's all I have to say."}]}]
|
ifeval
|
multi
|
Include keywords ['issue', 'pound', 'share', 'truth'] in the response. In your response, the letter f should appear less than 9 times. Your response should contain less than 29 sentences. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase.
|
personas_math_easy_md6cwn5i2ar66gkd61r0fype
|
[
{
"content": "Alex is an experienced Google Cloud engineer. He is setting up a series of training sessions on Google Cloud SQL for his team. Each session is designed to handle 12 participants, and he plans to conduct a total of 8 sessions. If the cost of setting up each session is $150, how much will Alex spend in total on setting up all the sessions? Additionally, if each participant is expected to save 2 hours per week on their tasks due to the improved efficiencies from the training, and there are 10 weeks of work remaining in the quarter, how many total hours will all participants save by the end of the quarter? At the end of your response, please explicitly add a postscript starting with Postscript: Include keywords ['cat', 'clue', 'matter', 'tune'] in the response.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:postscript', 'keywords:existence'], 'kwargs': [{'postscript_marker': 'Postscript:'}, {'keywords': ['cat', 'clue', 'matter', 'tune']}]}]
|
ifeval
|
multi
|
At the end of your response, please explicitly add a postscript starting with Postscript: Include keywords ['cat', 'clue', 'matter', 'tune'] in the response.
|
ai2-adapt-dev/tulu_v3.9_wildchat_100k_41826
|
[
{
"content": "Из этого отзыва создай пять новых отзывов, о неудачной покупке автомобиля в салоне Рт Моторс. Пиши разные отзывы. Не повторяйся! Пиши эмоционально, словно ты обиженный покупатель, с возмущением. Пиши от первого лица. Указывай разные модели автомобилей. Этот отзыв возьми в качестве примера: позвонил в салон. И что вы думаете? Подтвердили буква в букву информацию из рекламы. Хендай Элантра красного цвета за 1 млн 100 рублей. Кредит с ежемесячным платежом 17917 рублей, подробнее смогут рассказать условия, когда приеду. Спросил, когда лучше подъехать, сказали приезжайте завтра до трех часов дня, так как тогда типа еще дополнительную скидку могут сделать еще тысяч двадцать. Уууу, это просто байки, ребят. Я приехал с раскатанной губой прямо к открытию, даже минут за десять. Общался с ними часа два. За это время мне показали машину, которая мне понравилась, подтвердили цену в каталоге, а потом постепенно объяснили, что да, первоначальная цена именно такая и таковой бы и осталась — но поймите, ставка центробанка 20%(хотя 17 вроде), поэтому кредит обойдется теперь дороже. Плюс обязательно придется оформить КАСКО и страхование жизни, без этого увы никак, так что вместо почти 8-ми тысяч в месяц если скалькулировать все получается сумма та-дам! 40916 р! Считайте сами настоящую стоимость хваленой «скидки», если офрмить на 5 лет — 2454960 р. , что и является на данный момент его нормальной стоимостью. При этом можно даже дешевле найти — за 2153300 р. At the end of your response, please explicitly add a postscript starting with P.S.: Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your response must have 6 sections. Mark the beginning of each section with SECTION X, such as:\nSECTION 1\n[content of section 1]\nSECTION 2\n[content of section 2]",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:postscript', 'detectable_format:number_highlighted_sections', 'detectable_format:json_format', 'detectable_format:multiple_sections'], 'kwargs': [{'postscript_marker': 'P.S.:'}, {'num_highlights': 6}, None, {'section_spliter': 'SECTION', 'num_sections': 6}]}]
|
ifeval
|
multi
|
At the end of your response, please explicitly add a postscript starting with P.S.: Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your response must have 6 sections. Mark the beginning of each section with SECTION X, such as:
SECTION 1
[content of section 1]
SECTION 2
[content of section 2]
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_15287
|
[
{
"content": "Olivia starts with 45 stickers on Monday. On Tuesday, she gives away a quarter of them to her friend. On Wednesday, she purchases 15 new stickers. On Thursday, she buys half as many stickers as she gave away on Tuesday. How many stickers does Olivia have on Thursday? Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. The response must contain at least 3 placeholders represented by square brackets, such as [address]. Wrap your entire response with double quotation marks. In your entire response, refrain from the use of any commas.",
"role": "user"
}
] |
[{'instruction_id': ['combination:two_responses', 'detectable_content:number_placeholders', 'startend:quotation', 'punctuation:no_comma'], 'kwargs': [None, {'num_placeholders': 3}, None, None]}]
|
ifeval
|
multi
|
Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. The response must contain at least 3 placeholders represented by square brackets, such as [address]. Wrap your entire response with double quotation marks. In your entire response, refrain from the use of any commas.
|
personahub_1hx10u136fx97dtq1qmanrt0
|
[
{
"content": "A financially-conscious vehicle owner is considering switching from a gasoline car to an electric car. The gasoline car has an average fuel efficiency of 25 miles per gallon and the cost of gasoline is $3.50 per gallon. The electric car has an energy consumption rate of 0.3 kilowatt-hours (kWh) per mile and the cost of electricity is $0.12 per kWh. The owner drives an average of 15,000 miles per year.\n\n1. Calculate the annual cost savings from switching to the electric car.\n\nAdditionally, the owner is interested in smart technologies and considers installing a solar panel system to charge the electric car. The initial installation cost of the solar panel system is $10,000, and it can generate enough electricity to cover the car's annual energy consumption. The owner expects the system to last for 20 years, with no additional costs apart from the initial installation.\n\n2. Determine the payback period for the solar panel system and the total savings over its lifetime, considering the annual cost savings from switching to the electric car. In your response, the letter o should appear less than 7 times. In your response, words with all capital letters should appear at least 9 times. At the end of your response, please explicitly add a postscript starting with P.P.S.: First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)",
"role": "user"
}
] |
[{'instruction_id': ['keywords:letter_frequency', 'change_case:capital_word_frequency', 'detectable_content:postscript', 'combination:repeat_prompt'], 'kwargs': [{'letter': 'o', 'let_frequency': 7, 'let_relation': 'less than'}, {'capital_frequency': 9, 'capital_relation': 'at least'}, {'postscript_marker': 'P.P.S.:'}, {'prompt_to_repeat': "A financially-conscious vehicle owner is considering switching from a gasoline car to an electric car. The gasoline car has an average fuel efficiency of 25 miles per gallon and the cost of gasoline is $3.50 per gallon. The electric car has an energy consumption rate of 0.3 kilowatt-hours (kWh) per mile and the cost of electricity is $0.12 per kWh. The owner drives an average of 15,000 miles per year.\n\n1. Calculate the annual cost savings from switching to the electric car.\n\nAdditionally, the owner is interested in smart technologies and considers installing a solar panel system to charge the electric car. The initial installation cost of the solar panel system is $10,000, and it can generate enough electricity to cover the car's annual energy consumption. The owner expects the system to last for 20 years, with no additional costs apart from the initial installation.\n\n2. Determine the payback period for the solar panel system and the total savings over its lifetime, considering the annual cost savings from switching to the electric car."}]}]
|
ifeval
|
multi
|
In your response, the letter o should appear less than 7 times. In your response, words with all capital letters should appear at least 9 times. At the end of your response, please explicitly add a postscript starting with P.P.S.: First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_12063
|
[
{
"content": "A company has a budget of $250 million. The company then sells 3 of its subsidiaries at $20 million each, and acquires 2 more at $30 million each. Additionally, it invests $50 million in new equipment. How much money is left in the company's budget in millions of dollars? In your response, the word second should appear at least 2 times. Your response must have 8 sections. Mark the beginning of each section with PARAGRAPH X, such as:\nPARAGRAPH 1\n[content of section 1]\nPARAGRAPH 2\n[content of section 2]",
"role": "user"
}
] |
[{'instruction_id': ['keywords:frequency', 'detectable_format:multiple_sections'], 'kwargs': [{'keyword': 'second', 'frequency': 2, 'relation': 'at least'}, {'section_spliter': 'PARAGRAPH', 'num_sections': 8}]}]
|
ifeval
|
multi
|
In your response, the word second should appear at least 2 times. Your response must have 8 sections. Mark the beginning of each section with PARAGRAPH X, such as:
PARAGRAPH 1
[content of section 1]
PARAGRAPH 2
[content of section 2]
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_48875
|
[
{
"content": "Provided is a piece of erroneous Python code that is intended to identify and count prime numbers within a specific range of 0 to 100. Your task is to analyze and repair the flaws in the code so that it successfully accomplishes its goal. In addition to correcting the existing errors, the revised code should also be optimized for efficiency.\n\nThe erroneous code:\n\n```python\ndef count_primes(n):\n count = 0\n for i in range(2, n):\n prime = True\n for j in range(2, i):\n if (i % j == 0):\n prime = False\n if prime:\n count += 1\n return count\n\nprint(count_primes(100))\n```\n\nAdditionally, enhance the problem by counting twin primes within this range. A twin prime pair is a pair of primes that have a gap of two. For instance, (3, 5), (5, 7), and (11, 13) are twin primes. \n\nHow would you modify the above corrected code to also count the twin primes found within the range of 0 to 100? Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Do not include keywords ['alcohol', 'dot', 'doubt', 'top'] in the response. There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** At the end of your response, please explicitly add a postscript starting with Postscript: Your answer must contain exactly 3 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2",
"role": "user"
}
] |
[{'instruction_id': ['combination:two_responses', 'keywords:forbidden_words', 'length_constraints:number_paragraphs', 'detectable_content:postscript', 'detectable_format:number_bullet_lists'], 'kwargs': [None, {'forbidden_words': ['alcohol', 'dot', 'doubt', 'top']}, {'num_paragraphs': 5}, {'postscript_marker': 'Postscript:'}, {'num_bullets': 3}]}]
|
ifeval
|
multi
|
Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Do not include keywords ['alcohol', 'dot', 'doubt', 'top'] in the response. There should be 5 paragraphs. Paragraphs are separated with the markdown divider: *** At the end of your response, please explicitly add a postscript starting with Postscript: Your answer must contain exactly 3 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2
|
ai2-adapt-dev/tulu_v3.9_aya_100k_22012
|
[
{
"content": "ಈ ವಿಸ್ತಾರವಾದ ಪ್ರಶ್ನೆಗೆ ಉತ್ತರವನ್ನು ರೂಪಿಸಿರಿ: ಬೆಟ್ಟಿ ವೈಟ್ ಅಮೆರಿಕನ್ ಟೆಲಿವಿಷನ್ ಹಾಸ್ಯ ಸರಣಿ \"ದಿ ಗೋಲ್ಡನ್ ಗರ್ಲ್ಸ್\" ನಂತರ ಬಂದ ಸ್ಪಿನ್-ಆಫಿನ ಹೆಸರೇನು ? Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Highlight at least 2 sections in your answer with markdown, i.e. *highlighted section*. Your answer must contain exactly 8 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 Your entire response should be in English, and in all capital letters. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:title', 'detectable_format:number_highlighted_sections', 'detectable_format:number_bullet_lists', 'change_case:english_capital', 'combination:two_responses'], 'kwargs': [None, {'num_highlights': 2}, {'num_bullets': 8}, None, None]}]
|
ifeval
|
multi
|
Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Highlight at least 2 sections in your answer with markdown, i.e. *highlighted section*. Your answer must contain exactly 8 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Your entire response should be in English, and in all capital letters. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.
|
personahub_lfphzm3emaw7n2zj56lt4kdy
|
[
{
"content": "A dedicated fan, who runs a fan page for a popular vlogger, is organizing a series of fan meetups in different cities. The fan has noticed a pattern in the attendance and wants to optimize the scheduling of these meetups to maximize the number of attendees.\n\n1. **Attendance Growth Model**:\n The number of attendees \\(A(t)\\) at a meetup in a city \\(t\\) months after the vlogger's last visit to that city follows the logistic growth model given by:\n \\[\n A(t) = \\frac{K}{1 + e^{-r(t - t_0)}}\n \\]\n where:\n - \\(K\\) is the carrying capacity (maximum number of attendees),\n - \\(r\\) is the growth rate,\n - \\(t_0\\) is the inflection point (time in months when the growth rate is maximum).\n\n Given the parameters \\(K = 1000\\), \\(r = 0.3\\), and \\(t_0 = 4\\), calculate the number of attendees 6 months after the vlogger’s last visit to that city.\n\n2. **Optimization of Meetups**:\n The fan wants to schedule meetups in such a way that the sum of the attendees over the next 12 months is maximized. Assume the fan can schedule one meetup per month and that the attendance in each month follows the logistic growth model as described above. Determine the optimal months (in terms of \\(t\\)) to schedule the meetups to maximize the total attendance over the 12-month period. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:title'], 'kwargs': [None]}]
|
ifeval
|
multi
|
Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.
|
personas_math_easy_dunuph6q2qd3ez8pnzmin557
|
[
{
"content": "As a passionate fan and alumnus of Beaufort High School, you decide to attend this year's homecoming football game. You buy a ticket for yourself and decide to treat 4 friends to tickets as well. Each ticket costs $8.50. At the game, you buy a Beaufort High School scarf for $12 and 5 hot dogs for you and your friends, with each hot dog costing $3.75. How much money do you spend in total on tickets, the scarf, and hot dogs? Your ENTIRE response should be in Vietnamese language, no other language is allowed. In your response, words with all capital letters should appear at least 2 times. Answer with less than 814 words. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
] |
[{'instruction_id': ['language:response_language', 'change_case:capital_word_frequency', 'length_constraints:number_words', 'change_case:english_lowercase'], 'kwargs': [{'language': 'vi'}, {'capital_frequency': 2, 'capital_relation': 'at least'}, {'num_words': 814, 'relation': 'less than'}, None]}]
|
ifeval
|
multi
|
Your ENTIRE response should be in Vietnamese language, no other language is allowed. In your response, words with all capital letters should appear at least 2 times. Answer with less than 814 words. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_10148
|
[
{
"content": "Rafael has 20 apples. He sold 12 apples to his classmates for $1.50 each, while 5 other apples were sold to his neighbors for $2 each, and he kept 3 apples for his family. How much money did Rafael earn after selling 17 apples? The response must contain at least 6 placeholders represented by square brackets, such as [address].",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:number_placeholders'], 'kwargs': [{'num_placeholders': 6}]}]
|
ifeval
|
multi
|
The response must contain at least 6 placeholders represented by square brackets, such as [address].
|
ai2-adapt-dev/flan_v2_converted_7675
|
[
{
"content": "Next Question: Test for natural language inference.\nPremise: \"A couple just got married and are taking a picture with family.\"\nHypothesis: \"A couple just got divorced.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nMy Answer: Let's think. A couple cannot be both married and divorced to each other simultaneously. The answer is no.\n--\nNext Question: Can we conclude from \"A young girl in a pink and blue wetsuit and oversized red flip-flops presents a little red ball to a big black dog while another dog looks on.\" that \"A young girl is playing with her dog.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nMy Answer: Let's think. A girl presents a ball to a dog is playing with the dog. The answer is yes.\n--\nNext Question: Premise: \"A man in checkered shorts stacks wooden crates.\"\nBased on this premise, can we conclude that the hypothesis \"A man in checkered shorts wearing a hawaiian shirt.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nMy Answer: Your response must have 8 sections. Mark the beginning of each section with SECTION X, such as:\nSECTION 1\n[content of section 1]\nSECTION 2\n[content of section 2] Answer with at least 910 words. The response must contain at least 4 placeholders represented by square brackets, such as [address]. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:multiple_sections', 'length_constraints:number_words', 'detectable_content:number_placeholders', 'detectable_format:title', 'detectable_format:constrained_response'], 'kwargs': [{'section_spliter': 'SECTION', 'num_sections': 8}, {'num_words': 910, 'relation': 'at least'}, {'num_placeholders': 4}, None, None]}]
|
ifeval
|
multi
|
Your response must have 8 sections. Mark the beginning of each section with SECTION X, such as:
SECTION 1
[content of section 1]
SECTION 2
[content of section 2] Answer with at least 910 words. The response must contain at least 4 placeholders represented by square brackets, such as [address]. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_98601
|
[
{
"content": "Create a Python dictionary from two given lists.\nlist1 = ['a', 'b', 'c'] \nlist2 = [1, 2, 3] Your response should contain at least 4 sentences. Answer with at least 791 words.",
"role": "user"
}
] |
[{'instruction_id': ['length_constraints:number_sentences', 'length_constraints:number_words'], 'kwargs': [{'num_sentences': 4, 'relation': 'at least'}, {'num_words': 791, 'relation': 'at least'}]}]
|
ifeval
|
multi
|
Your response should contain at least 4 sentences. Answer with at least 791 words.
|
personahub_9emeftdsegkpahf9b49bs1gv
|
[
{
"content": "A new generation folk music enthusiast has a collection of 500 songs that includes a mix of new generation folk music, classic rock, and vintage jazz. The ratio of new generation folk songs to classic rock songs is 3:2, and the ratio of classic rock songs to vintage jazz songs is 4:3.\n\n1. Determine the number of songs in each category (new generation folk, classic rock, and vintage jazz) in the collection.\n \n2. The enthusiast creates a playlist where the probability of randomly selecting a new generation folk song is increased by 20% more than its proportion in the original collection. Calculate the new probability of selecting a classic rock song from this playlist. In your entire response, refrain from the use of any commas. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your response should contain less than 9 sentences. In your response, the letter q should appear less than 4 times.",
"role": "user"
}
] |
[{'instruction_id': ['punctuation:no_comma', 'detectable_format:title', 'length_constraints:number_sentences', 'keywords:letter_frequency'], 'kwargs': [None, None, {'num_sentences': 9, 'relation': 'less than'}, {'letter': 'q', 'let_frequency': 4, 'let_relation': 'less than'}]}]
|
ifeval
|
multi
|
In your entire response, refrain from the use of any commas. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your response should contain less than 9 sentences. In your response, the letter q should appear less than 4 times.
|
ai2-adapt-dev/no_robots_converted_2917
|
[
{
"content": "What are three class archetypes in RPGs? Give a short description of their attributes and the attire they wear. Give an example of each in a different video game. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. There should be 6 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 1 must start with word heat.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:json_format', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [None, {'num_paragraphs': 6, 'nth_paragraph': 1, 'first_word': 'heat'}]}]
|
ifeval
|
multi
|
Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. There should be 6 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 1 must start with word heat.
|
ai2-adapt-dev/numinamath_tir_math_decontaminated_52126
|
[
{
"content": "There are 30 people in my math class. 12 of them have cool dads, 15 of them have cool moms, and 9 of them have cool dads and cool moms. How many people have moms and dads who are both uncool? In your response, the word technology should appear at least 1 times. Your answer must contain exactly 5 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 Your ENTIRE response should be in Gujarati language, no other language is allowed. Your response should contain at least 1 sentences. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)",
"role": "user"
}
] |
[{'instruction_id': ['keywords:frequency', 'detectable_format:number_bullet_lists', 'language:response_language', 'length_constraints:number_sentences', 'combination:repeat_prompt'], 'kwargs': [{'keyword': 'technology', 'frequency': 1, 'relation': 'at least'}, {'num_bullets': 5}, {'language': 'gu'}, {'num_sentences': 1, 'relation': 'at least'}, {'prompt_to_repeat': 'There are 30 people in my math class. 12 of them have cool dads, 15 of them have cool moms, and 9 of them have cool dads and cool moms. How many people have moms and dads who are both uncool?'}]}]
|
ifeval
|
multi
|
In your response, the word technology should appear at least 1 times. Your answer must contain exactly 5 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Your ENTIRE response should be in Gujarati language, no other language is allowed. Your response should contain at least 1 sentences. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)
|
personahub_uncyaulkc6exu34fu92xti0f
|
[
{
"content": "As a graduate student analyzing the architectural evolution of Roman aqueducts, you are tasked with understanding the structural efficiency and material usage optimization over time. Consider two Roman aqueducts: Aqueduct A built in the 1st century AD and Aqueduct B built in the 4th century AD. Both aqueducts are composed of a series of semicircular arches of uniform width but differing heights and spans.\n\n1. Aqueduct A has arches with a span of 10 meters and a height of 5 meters. Aqueduct B has arches with a span of 12 meters and a height of 6 meters. Using the principles of calculus, derive the expressions for the total volume of material used in constructing the arches of both aqueducts per kilometer. Assume the width of each arch is 1 meter and that the cross-section of the arches can be approximated by a rectangle topped with a semicircle.\n\n2. Suppose the material density of the stone used in both aqueducts is uniform and equal to 2400 kg/m³. Using the volume expressions derived in sub-problem 1, calculate the difference in weight for the material used per kilometer between Aqueduct A and Aqueduct B. Furthermore, analyze how the change in architectural design from Aqueduct A to Aqueduct B reflects an improvement in resource efficiency, considering the advancements in engineering techniques over the centuries. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:title'], 'kwargs': [None]}]
|
ifeval
|
multi
|
Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.
|
ai2-adapt-dev/tulu_v3.9_table_gpt_5k_2
|
[
{
"content": "# Task Description: Please relocate column \"17\" from the table to the rightmost position. Share the updated table with the column rearranged.\n\nInput:\n|Year|Entrants|4|5|6|7|8|9|10|11|12|13|Chassis|14|16|17|18|Engines|\n|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|\n|2003|Mo Nunn Racing|5|3|6|13|18|7|6|7|18|14|G-Force GF09|9|18|7|nan|Toyota Indy V8|\n|2005|Target Chip Ganassi Racing|nan|nan|nan|nan|nan|nan|nan|nan|nan|nan|Panoz GF09C|14|nan|4|nan|Toyota Indy V8|\n|2003|Mo Nunn Racing|nan|nan|nan|nan|nan|5|1|16|20|15|G-Force GF09|nan|nan|nan|nan|Toyota Indy V8|\n|2005|Target Chip Ganassi Racing|nan|24|11|22|18|6|13|19|23|16|Panoz GF09C|7|19|1*|10|Toyota Indy V8|\n|2004|Target Chip Ganassi Racing|25|8|20|11|4|19|13|10|4|6|G-Force GF09B|15|DNS|nan|nan|Toyota Indy V8|\n\nOutput:\n|Year|Entrants|4|5|6|7|8|9|10|11|12|13|Chassis|14|16|18|Engines|17|\n|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|\n|2003|Mo Nunn Racing|5|3|6|13|18|7|6|7|18|14|G-Force GF09|9|18|nan|Toyota Indy V8|7|\n|2005|Target Chip Ganassi Racing|nan|nan|nan|nan|nan|nan|nan|nan|nan|nan|Panoz GF09C|14|nan|nan|Toyota Indy V8|4|\n|2003|Mo Nunn Racing|nan|nan|nan|nan|nan|5|1|16|20|15|G-Force GF09|nan|nan|nan|Toyota Indy V8|nan|\n|2005|Target Chip Ganassi Racing|nan|24|11|22|18|6|13|19|23|16|Panoz GF09C|7|19|10|Toyota Indy V8|1*|\n|2004|Target Chip Ganassi Racing|25|8|20|11|4|19|13|10|4|6|G-Force GF09B|15|DNS|nan|Toyota Indy V8|nan|\n\n\nInput:\n|Year|Entrants|4|5|6|7|8|9|10|11|12|13|Chassis|14|16|17|18|Engines|\n|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|\n|2006|Target Chip Ganassi Racing|nan|1|nan|nan|nan|nan|nan|nan|nan|4*|Panoz GF09C|nan|nan|nan|nan|Honda HI6R V8|\n|2003|Access Motorsports|11|18|12|8|16|10|8|15|17|DNS|G-Force GF09|14|8|nan|nan|Honda HI3R V8|\n|2004|Target Chip Ganassi Racing|INDY|TXS|RIR|KAN|NSH|MIL|MCH|KTY|PPIR|NAZ|G-Force GF09B|CHI|FON|TXS|nan|Toyota Indy V8|\n|2005|Target Chip Ganassi Racing|nan|nan|nan|nan|nan|nan|nan|17|15|DNS|Panoz GF09C|nan|16|nan|17|Toyota Indy V8|\n|2005|Target Chip Ganassi Racing|nan|24|11|22|18|6|13|19|23|16|Panoz GF09C|7|19|1*|10|Toyota Indy V8|\n\nOutput:\n|Year|Entrants|4|5|6|7|8|9|10|11|12|13|Chassis|14|16|18|Engines|17|\n|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|\n|2006|Target Chip Ganassi Racing|nan|1|nan|nan|nan|nan|nan|nan|nan|4*|Panoz GF09C|nan|nan|nan|Honda HI6R V8|nan|\n|2003|Access Motorsports|11|18|12|8|16|10|8|15|17|DNS|G-Force GF09|14|8|nan|Honda HI3R V8|nan|\n|2004|Target Chip Ganassi Racing|INDY|TXS|RIR|KAN|NSH|MIL|MCH|KTY|PPIR|NAZ|G-Force GF09B|CHI|FON|nan|Toyota Indy V8|TXS|\n|2005|Target Chip Ganassi Racing|nan|nan|nan|nan|nan|nan|nan|17|15|DNS|Panoz GF09C|nan|16|17|Toyota Indy V8|nan|\n|2005|Target Chip Ganassi Racing|nan|24|11|22|18|6|13|19|23|16|Panoz GF09C|7|19|10|Toyota Indy V8|1*|\n\n\nInput:\n|Year|Entrants|4|5|6|7|8|9|10|11|12|13|Chassis|14|16|17|18|Engines|\n|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|\n|2003|Ganassi Racing|INDY|TXS|PPIR|RIR|KAN|NSH|MCH|GAT|KTY|NAZ|G-Force GF09|CHI|FON|TXS|nan|Toyota Indy V8|\n|2003|Ganassi Racing|17|6|1*|1*|6|2|5|15|2|16|G-Force GF09|2|2|2|nan|Toyota Indy V8|\n|2003|Ganassi Racing|4*|18*|8|18|9|10|3|4|10|19|G-Force GF09|5*|5*|15|nan|Toyota Indy V8|\n|2003|Team Penske|1|8|nan|nan|nan|nan|nan|nan|nan|nan|G-Force GF09|nan|15|nan|nan|Toyota Indy V8|\n|2003|A. J. Foyt Enterprises|nan|nan|nan|nan|nan|nan|nan|nan|nan|nan|G-Force GF09|nan|nan|nan|nan|Toyota Indy V8|\n\nOutput:\n Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') There should be 7 paragraphs. Paragraphs are separated with the markdown divider: *** Your response should contain at least 3 sentences. There should be 5 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 4 must start with word deep.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:constrained_response', 'length_constraints:number_paragraphs', 'length_constraints:number_sentences', 'length_constraints:nth_paragraph_first_word'], 'kwargs': [None, {'num_paragraphs': 7}, {'num_sentences': 3, 'relation': 'at least'}, {'num_paragraphs': 5, 'nth_paragraph': 4, 'first_word': 'deep'}]}]
|
ifeval
|
multi
|
Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') There should be 7 paragraphs. Paragraphs are separated with the markdown divider: *** Your response should contain at least 3 sentences. There should be 5 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 4 must start with word deep.
|
personahub_716xy4gl5t5d1y0cet3ve6lt
|
[
{
"content": "Alex, who runs a local tennis academy in the town where they grew up, is trying to optimize the use of the academy's courts. The academy has 5 tennis courts, and Alex has observed that the number of players wishing to book a court follows a Poisson distribution with a mean rate of 12 players per hour.\n\n1. Assuming that each player books a court for 1 hour, what is the probability that all 5 courts are occupied at any given hour? Use the properties of the Poisson distribution to derive your answer.\n\n2. If Alex wants to ensure that the probability of having at least one available court (given the mean rate of 12 players per hour) is at least 95%, how many additional courts should Alex consider adding to the academy? Formulate and solve the problem using appropriate probability techniques and inequalities. At the end of your response, please explicitly add a postscript starting with P.P.S.: Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your response must have 1 sections. Mark the beginning of each section with PARAGRAPH X, such as:\nPARAGRAPH 1\n[content of section 1]\nPARAGRAPH 2\n[content of section 2] There should be 6 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:postscript', 'detectable_format:title', 'detectable_format:multiple_sections', 'length_constraints:number_paragraphs'], 'kwargs': [{'postscript_marker': 'P.P.S.:'}, None, {'section_spliter': 'PARAGRAPH', 'num_sections': 1}, {'num_paragraphs': 6}]}]
|
ifeval
|
multi
|
At the end of your response, please explicitly add a postscript starting with P.P.S.: Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Your response must have 1 sections. Mark the beginning of each section with PARAGRAPH X, such as:
PARAGRAPH 1
[content of section 1]
PARAGRAPH 2
[content of section 2] There should be 6 paragraphs. Paragraphs are separated with the markdown divider: ***
|
ai2-adapt-dev/flan_v2_converted_71278
|
[
{
"content": "Given the sentence \"A boy selling lemonade for$ 1 rides his bike with no hands as he advertises his product to a long line of people.\" is it true that \"The boy is riding a bike with training wheels wile advertising his lemonade stand.\"?\n--\nA boy is performing a lemonade stand in front of people for sale.. The answer is: it is not possible to tell.\n----\nPremise: \"A man sits on a concrete ledge with his bicycle by his side while another man walks toward him holding the hand of a young girl and carrying a baby in a front pack.\"\nHypothesis: \"A man sits next to his bicycle.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\n--\nNext to his bicycle is a rephrase of with his bicycle by his side.. The answer is: yes.\n----\nCan we conclude from \"One adult sitting next to three young children eating ice cream on some steps.\" that \"A family is eating pizza on the couch.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n--\n Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:json_format'], 'kwargs': [None]}]
|
ifeval
|
multi
|
Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.
|
personahub_ex1cfvf3v26t2hso2wxnhmys
|
[
{
"content": "As a longtime bakery owner, you decide to analyze the impact of new catering services on your business. You have historical data showing that your bakery's daily revenue, \\( R(t) \\) in dollars, can be modeled by the function \\( R(t) = 1500 + 500\\sin(\\frac{\\pi}{30}t) \\), where \\( t \\) is the number of days since the start of the year. \n\n1. Recently, a new catering service has started and is predicted to cause a linear decrease in your daily revenue at a rate of \\( 10t \\) dollars per day. Determine the number of days, \\( t \\), in the first year when your revenue will drop below $1000. Formulate and solve the inequality to find these days.\n\n2. To counteract this threat, you plan to introduce a new product line that increases your daily revenue by a constant rate of \\( c \\) dollars per day. Determine the minimum value of \\( c \\) required to ensure that your revenue never drops below $1000 at any day \\( t \\) within the first year, considering the impact of the catering service. The response must contain at least 1 placeholders represented by square brackets, such as [address]. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') The response must contain at least 2 placeholders represented by square brackets, such as [address]. At the end of your response, please explicitly add a postscript starting with P.P.S Your response must have 4 sections. Mark the beginning of each section with PARAGRAPH X, such as:\nPARAGRAPH 1\n[content of section 1]\nPARAGRAPH 2\n[content of section 2]",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:number_placeholders', 'detectable_format:constrained_response', 'detectable_content:number_placeholders', 'detectable_content:postscript', 'detectable_format:multiple_sections'], 'kwargs': [{'num_placeholders': 1}, None, {'num_placeholders': 2}, {'postscript_marker': 'P.P.S'}, {'section_spliter': 'PARAGRAPH', 'num_sections': 4}]}]
|
ifeval
|
multi
|
The response must contain at least 1 placeholders represented by square brackets, such as [address]. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') The response must contain at least 2 placeholders represented by square brackets, such as [address]. At the end of your response, please explicitly add a postscript starting with P.P.S Your response must have 4 sections. Mark the beginning of each section with PARAGRAPH X, such as:
PARAGRAPH 1
[content of section 1]
PARAGRAPH 2
[content of section 2]
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_27752
|
[
{
"content": "Together Felipe and Emilio needed a combined time of 7.5 years to build their homes. Felipe finished in half the time of Emilio. How many months did it take Felipe to build his house? In your response, the word guess should appear at least 3 times. Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*. Your response must have 2 sections. Mark the beginning of each section with PARAGRAPH X, such as:\nPARAGRAPH 1\n[content of section 1]\nPARAGRAPH 2\n[content of section 2] Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:frequency', 'detectable_format:number_highlighted_sections', 'detectable_format:multiple_sections', 'detectable_format:json_format'], 'kwargs': [{'keyword': 'guess', 'frequency': 3, 'relation': 'at least'}, {'num_highlights': 8}, {'section_spliter': 'PARAGRAPH', 'num_sections': 2}, None]}]
|
ifeval
|
multi
|
In your response, the word guess should appear at least 3 times. Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*. Your response must have 2 sections. Mark the beginning of each section with PARAGRAPH X, such as:
PARAGRAPH 1
[content of section 1]
PARAGRAPH 2
[content of section 2] Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_103098
|
[
{
"content": "Implement a function that converts every character of a given string into its corresponding upper case, but without using any built-in methods for case conversion in Python. Use ASCII character codes to solve this task.\nstring = \"I love programming.\" In your entire response, refrain from the use of any commas. Your answer must contain exactly 1 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2",
"role": "user"
}
] |
[{'instruction_id': ['punctuation:no_comma', 'detectable_format:number_bullet_lists'], 'kwargs': [None, {'num_bullets': 1}]}]
|
ifeval
|
multi
|
In your entire response, refrain from the use of any commas. Your answer must contain exactly 1 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2
|
personas_math_easy_gtcvxvnz9hymh38cml6tc6nw
|
[
{
"content": "Alex, a skilled maintenance technician, was called to repair a series of industrial machines in a factory. Each machine needs a specific amount of time for troubleshooting and repairs. The first machine takes 45 minutes to troubleshoot and 30 minutes to repair. The second machine takes 60 minutes to troubleshoot and half the time of the first machine's repair time to repair itself. The third machine requires 90 minutes in total for both troubleshooting and repair, with troubleshooting taking twice as long as the repair. \n\nIf Alex starts working at 8:00 AM and takes a 15-minute break after completing the repairs on each machine, what time will Alex finish repairing all three machines? In your response, the word engineer should appear at least 4 times. The response must contain at least 2 placeholders represented by square brackets, such as [address]. In your response, words with all capital letters should appear at least 26 times.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:frequency', 'detectable_content:number_placeholders', 'change_case:capital_word_frequency'], 'kwargs': [{'keyword': 'engineer', 'frequency': 4, 'relation': 'at least'}, {'num_placeholders': 2}, {'capital_frequency': 26, 'capital_relation': 'at least'}]}]
|
ifeval
|
multi
|
In your response, the word engineer should appear at least 4 times. The response must contain at least 2 placeholders represented by square brackets, such as [address]. In your response, words with all capital letters should appear at least 26 times.
|
ai2-adapt-dev/tulu_v3.9_wildchat_100k_8046
|
[
{
"content": "Generate a description with keywords and SEOs for Pikachu Masterpiece Design | Versatile Art for Mugs, Shirts, Canvas Prints | Unique Pop Culture Illustration | Geek Chic Decor. Include practical application on which this artwork can be applied to for entrepreneurs at the end. Include details on dimensions: 1080x1080 and has 3 image variations. Include buyer has full rights to resale and commercial usage. Don't include HTML or '<br/>' for formatting only newline '\n' Your response must have 10 sections. Mark the beginning of each section with SECTION X, such as:\nSECTION 1\n[content of section 1]\nSECTION 2\n[content of section 2]",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:multiple_sections'], 'kwargs': [{'section_spliter': 'SECTION', 'num_sections': 10}]}]
|
ifeval
|
multi
|
Your response must have 10 sections. Mark the beginning of each section with SECTION X, such as:
SECTION 1
[content of section 1]
SECTION 2
[content of section 2]
|
personahub_do4kkxskkofvdwap7d0dovc3
|
[
{
"content": "A senior product designer at a green tech company is working with a team of interns to design a new solar panel system. The aim is to maximize energy efficiency and innovation in a new prototype. The solar panel system consists of two main components: an array of photovoltaic cells and an innovative energy storage unit. The photovoltaic cells convert sunlight into electricity, while the storage unit uses a new type of battery technology to store the energy.\n\n1. The efficiency of the photovoltaic cells is given by the function \\(E(x) = \\frac{4x}{x^2 + 1}\\), where \\(x\\) represents the angle of incidence of sunlight in radians. Determine the angle \\(x\\) that maximizes the efficiency \\(E(x)\\) and find the maximum efficiency value.\n\n2. The energy storage unit uses a battery technology characterized by a discharge function \\(D(t) = Ae^{-kt}\\), where \\(A\\) and \\(k\\) are constants representing the initial charge and the rate of discharge, respectively, and \\(t\\) is time in hours. If the total energy stored after \\(T\\) hours is given by the integral \\(\\int_0^T D(t) \\, dt\\), and the maximum allowable discharge over a period of 10 hours is 60% of the initial charge, find the maximum value of \\(A\\) in terms of \\(k\\) that satisfies this condition. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:constrained_response'], 'kwargs': [None]}]
|
ifeval
|
multi
|
Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')
|
ai2-adapt-dev/tulu_v3.9_synthetic_finalresp_wildguardmixtrain_decontaminated_50k_3035
|
[
{
"content": "I've heard that card counting is not illegal, but that some casinos will kick you for it. Include keywords ['animal', 'contribution', 'kid', 'tension'] in the response. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all capital letters. At the end of your response, please explicitly add a postscript starting with P.S.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:existence', 'detectable_format:number_highlighted_sections', 'change_case:english_capital', 'detectable_content:postscript'], 'kwargs': [{'keywords': ['animal', 'contribution', 'kid', 'tension']}, {'num_highlights': 3}, None, {'postscript_marker': 'P.S.'}]}]
|
ifeval
|
multi
|
Include keywords ['animal', 'contribution', 'kid', 'tension'] in the response. Highlight at least 3 sections in your answer with markdown, i.e. *highlighted section*. Your entire response should be in English, and in all capital letters. At the end of your response, please explicitly add a postscript starting with P.S.
|
personahub_d94rzshdwl7soowu9bzyvrai
|
[
{
"content": "A mother is organizing a community event to raise awareness about equal employment opportunities for individuals with disabilities. She plans to set up a booth at the event where she will distribute information pamphlets and sell hand-made crafts created by her adult child who has autism. \n\n1. If the cost to produce each craft is represented by the polynomial \\( C(x) = 3x^2 - 5x + 2 \\), where \\( x \\) is the number of crafts, and she plans to make a total of 10 crafts, calculate the total production cost. \n\n2. She wants to ensure that the revenue from selling these crafts is at least $150 to cover expenses and make a small profit. If she sells each craft for $15, solve the inequality to find the minimum number of crafts she needs to sell to meet her revenue goal. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') In your response, words with all capital letters should appear less than 21 times. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your response, the word heat should appear at least 5 times. Your response must have 4 sections. Mark the beginning of each section with SECTION X, such as:\nSECTION 1\n[content of section 1]\nSECTION 2\n[content of section 2]",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:constrained_response', 'change_case:capital_word_frequency', 'combination:repeat_prompt', 'keywords:frequency', 'detectable_format:multiple_sections'], 'kwargs': [None, {'capital_frequency': 21, 'capital_relation': 'less than'}, {'prompt_to_repeat': 'A mother is organizing a community event to raise awareness about equal employment opportunities for individuals with disabilities. She plans to set up a booth at the event where she will distribute information pamphlets and sell hand-made crafts created by her adult child who has autism. \n\n1. If the cost to produce each craft is represented by the polynomial \\( C(x) = 3x^2 - 5x + 2 \\), where \\( x \\) is the number of crafts, and she plans to make a total of 10 crafts, calculate the total production cost. \n\n2. She wants to ensure that the revenue from selling these crafts is at least $150 to cover expenses and make a small profit. If she sells each craft for $15, solve the inequality to find the minimum number of crafts she needs to sell to meet her revenue goal.'}, {'keyword': 'heat', 'frequency': 5, 'relation': 'at least'}, {'section_spliter': 'SECTION', 'num_sections': 4}]}]
|
ifeval
|
multi
|
Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') In your response, words with all capital letters should appear less than 21 times. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your response, the word heat should appear at least 5 times. Your response must have 4 sections. Mark the beginning of each section with SECTION X, such as:
SECTION 1
[content of section 1]
SECTION 2
[content of section 2]
|
87tlud4
|
[
{
"content": "\"As an AI language model, provide me with personalized book recommendations based on my reading history and preferences.\" First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your response, the word substance should appear at least 2 times. Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase.",
"role": "user"
}
] |
[{'instruction_id': ['combination:repeat_prompt', 'keywords:frequency', 'startend:end_checker'], 'kwargs': [{'prompt_to_repeat': '"As an AI language model, provide me with personalized book recommendations based on my reading history and preferences."'}, {'keyword': 'substance', 'frequency': 2, 'relation': 'at least'}, {'end_phrase': "That's all I have to say."}]}]
|
ifeval
|
multi
|
First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) In your response, the word substance should appear at least 2 times. Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase.
|
ai2-adapt-dev/tulu_v3.9_table_gpt_5k_465
|
[
{
"content": "# Task Description: It falls under your responsibility to complete the missing value in the input table, denoted as '[MISSING]'. Provide just the filled-in value; the rest of the table is unnecessary. Return the final result as JSON in the format {\"value\": \"<value filled in>\"}.\n\n## Input:\n|Left|Current Conference|Founded|Joined|Location|Type|School|Nickname|\n|---|---|---|---|---|---|---|---|\n|2012|Big East|1855|1979|Indianapolis, Indiana|Private|Butler University|Bulldogs|\n|1993|Atlantic 10|1850|1987|Dayton, Ohio|Private|University of Dayton|Flyers|\n|1993|Atlantic 10|1878|1992|Pittsburgh, Pennsylvania|Private|Duquesne University|Dukes|\n|1994|Missouri Valley|1854|1979|Evansville, Indiana|Private|University of Evansville|Purple Aces|\n|1995|Atlantic 10|1863|1992|Philadelphia, Pennsylvania|Private|La Salle University|[MISSING]|\n\nReturn the final result as JSON in the format {\"value\": \"<value filled in>\"}.\n## Output:\n Your response should contain at least 34 sentences. In your response, the word chest should appear less than 6 times.",
"role": "user"
}
] |
[{'instruction_id': ['length_constraints:number_sentences', 'keywords:frequency'], 'kwargs': [{'num_sentences': 34, 'relation': 'at least'}, {'keyword': 'chest', 'frequency': 6, 'relation': 'less than'}]}]
|
ifeval
|
multi
|
Your response should contain at least 34 sentences. In your response, the word chest should appear less than 6 times.
|
ai2-adapt-dev/flan_v2_converted_66703
|
[
{
"content": "Consider the question. Test for natural language inference.\nPremise: \"The sky is very blue and the grass is very green at a golf course while a girl looks into a golf hole for a ball.\"\nHypothesis: \"The girl is at the golf course.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n If the answer is 'yes'; explain the reasoning: At the end of your response, please explicitly add a postscript starting with P.S At the end of your response, please explicitly add a postscript starting with P.P.S Answer with less than 986 words.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_content:postscript', 'detectable_content:postscript', 'length_constraints:number_words'], 'kwargs': [{'postscript_marker': 'P.S'}, {'postscript_marker': 'P.P.S'}, {'num_words': 986, 'relation': 'less than'}]}]
|
ifeval
|
multi
|
At the end of your response, please explicitly add a postscript starting with P.S At the end of your response, please explicitly add a postscript starting with P.P.S Answer with less than 986 words.
|
personahub_ygv057kwgnl7bzcrchr3u5i2
|
[
{
"content": "Dr. Green, a doctor who believes in the healing power of nature, is designing a wellness park that incorporates various natural elements to maximize the health benefits for her patients. The park is divided into two main sections: a circular walking trail and a rectangular meditation garden. The walking trail is a perfect circle with a radius of \\( r \\) meters, and the meditation garden is a rectangle with dimensions \\( a \\) meters by \\( b \\) meters.\n\n1. Dr. Green wants to ensure that the total area of the park dedicated to natural elements is exactly 1 hectare (10,000 square meters). If the area of the walking trail is equal to the area of the meditation garden, express \\( r \\) in terms of \\( a \\) and \\( b \\).\n\n2. To enhance the healing experience, Dr. Green plans to plant a certain number of trees along the perimeter of the circular walking trail such that the trees are evenly spaced. She wants the number of trees to be a prime number greater than 10. If the distance between each pair of consecutive trees is \\( d \\) meters, find a condition involving \\( r \\) and \\( d \\) that ensures the total number of trees is a prime number. In your response, the word reference should appear less than 1 times.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:frequency'], 'kwargs': [{'keyword': 'reference', 'frequency': 1, 'relation': 'less than'}]}]
|
ifeval
|
multi
|
In your response, the word reference should appear less than 1 times.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_2291
|
[
{
"content": "Kasashe nawa ne masu cin gashin kansu a nahiyar Turai? Answer with at least 913 words. There should be 4 paragraphs. Paragraphs are separated with the markdown divider: *** Your entire response should be in English, and in all capital letters.",
"role": "user"
}
] |
[{'instruction_id': ['length_constraints:number_words', 'length_constraints:number_paragraphs', 'change_case:english_capital'], 'kwargs': [{'num_words': 913, 'relation': 'at least'}, {'num_paragraphs': 4}, None]}]
|
ifeval
|
multi
|
Answer with at least 913 words. There should be 4 paragraphs. Paragraphs are separated with the markdown divider: *** Your entire response should be in English, and in all capital letters.
|
ai2-adapt-dev/flan_v2_converted_958
|
[
{
"content": "Use reasoning to lead to the answer of the following question:\nIf I am a spectator at a movie theater, what am I likely watching?\nOptions:\n- watch event\n- performance\n- demonstration\n- sporting event\n- show\n Reasoning process: In your response, the letter d should appear less than 10 times. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Finish your response with this exact phrase The END.. No other words should follow this phrase.",
"role": "user"
}
] |
[{'instruction_id': ['keywords:letter_frequency', 'combination:two_responses', 'startend:end_checker'], 'kwargs': [{'letter': 'd', 'let_frequency': 10, 'let_relation': 'less than'}, None, {'end_phrase': 'The END.'}]}]
|
ifeval
|
multi
|
In your response, the letter d should appear less than 10 times. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Finish your response with this exact phrase The END.. No other words should follow this phrase.
|
personahub_5ox9ls0slz2698pwo6tzt24f
|
[
{
"content": "Ana, a Brazilian immigrant living in Chile, is an avid traveler and enjoys exploring both countries. She often travels between São Paulo (her hometown in Brazil) and Santiago (her current residence in Chile). To make her travels more efficient, she studies the optimal flight paths and fuel consumption of aircraft flying between these two cities.\n\nSub-problem 1: The direct distance between São Paulo and Santiago is approximately 3,000 kilometers. Ana is analyzing two potential flight paths. The first path is a direct flight, and the second path involves a stopover in Buenos Aires, which adds an additional 500 kilometers to the total distance. If the aircraft consumes fuel at a rate of 2.5 liters per kilometer and has an initial fuel efficiency of 0.8 liters per kilometer, calculate the total fuel consumption for both flight paths. Assume that the fuel efficiency decreases linearly by 0.01 liters per kilometer for every 100 kilometers flown.\n\nSub-problem 2: Ana is also interested in understanding the time efficiency of these flight paths. The average speed of the aircraft is 850 kilometers per hour. However, for each hour of flight, the aircraft loses 5% of its average speed due to altitude adjustments and air traffic control restrictions. Calculate the total flight time for both paths, considering the speed reduction. How much longer does the second path take compared to the first path? Your answer must contain exactly 2 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 Do not include keywords ['foundation', 'pound', 'print', 'stop'] in the response. Your response must have 6 sections. Mark the beginning of each section with PARAGRAPH X, such as:\nPARAGRAPH 1\n[content of section 1]\nPARAGRAPH 2\n[content of section 2] In your response, words with all capital letters should appear at least 7 times.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:number_bullet_lists', 'keywords:forbidden_words', 'detectable_format:multiple_sections', 'change_case:capital_word_frequency'], 'kwargs': [{'num_bullets': 2}, {'forbidden_words': ['foundation', 'pound', 'print', 'stop']}, {'section_spliter': 'PARAGRAPH', 'num_sections': 6}, {'capital_frequency': 7, 'capital_relation': 'at least'}]}]
|
ifeval
|
multi
|
Your answer must contain exactly 2 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Do not include keywords ['foundation', 'pound', 'print', 'stop'] in the response. Your response must have 6 sections. Mark the beginning of each section with PARAGRAPH X, such as:
PARAGRAPH 1
[content of section 1]
PARAGRAPH 2
[content of section 2] In your response, words with all capital letters should appear at least 7 times.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_43183
|
[
{
"content": "Apakah maksud \"ada ubi ada batas, ada hari boleh balas\"? There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)",
"role": "user"
}
] |
[{'instruction_id': ['length_constraints:number_paragraphs', 'combination:repeat_prompt'], 'kwargs': [{'num_paragraphs': 2}, {'prompt_to_repeat': 'Apakah maksud "ada ubi ada batas, ada hari boleh balas"?'}]}]
|
ifeval
|
multi
|
There should be 2 paragraphs. Paragraphs are separated with the markdown divider: *** First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence)
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_38235
|
[
{
"content": "Create a Python program to retrieve and list all the books in a given category in an online book store.\nCategory = \"Computer Science\" Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. In your response, words with all capital letters should appear at least 1 times. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:number_highlighted_sections', 'combination:two_responses', 'change_case:capital_word_frequency', 'detectable_format:json_format'], 'kwargs': [{'num_highlights': 8}, None, {'capital_frequency': 1, 'capital_relation': 'at least'}, None]}]
|
ifeval
|
multi
|
Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section*. Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. In your response, words with all capital letters should appear at least 1 times. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```.
|
ai2-adapt-dev/tulu_v3.9_wildchat_100k_78557
|
[
{
"content": "Reframe in polished discussion way and style \nThe problem with child narrators, however, becomes all the more pressing when the narrator is a girl child, as she has to navigate a complex and hostile terrain: she has to speak her truth and claim her authority as a child and as a woman in a culture that often ignores and marginalises both. She has to find her voice and identity in a narrative space that is influenced by the standards and desires of adult and male readers. She has to defy the labels and assumptions that are imposed on her gender and age and confront the powerful discourses that try to limit and shape her The question, then, that can be raised, is does the narrator’s (since the narrator in selected novels is a girl child) gender have any bearing on the text? Could the primacy of gender be such that it wields influence within the textual fabric itself? To what extent does the gender of the narrator infuse the narrative with layers of meaning, context, and interpretation that transcend the words on the page?. To recognize this specificity…. in recent years has led many narratologists to examine the significance of the gender of narrator on its narration. Susan Lanser, for example (1986), in her….., argues that gender is a category “that is relevant to the analysis of the structural features of narratives.” In order to understand the true “nature, form, and functioning of narrative” (Lanser) it is imperative to explore the implications of “sex, gender and/or sexuality” (Lanser) of the narrator or narrative. She claims that texts with, I would say girl child narrators, are more “polyphones”; it comprises different strands which need to be “identified” and “disentangled,” being multi-layered, and with different levels of meaning. Similarly Carson and others maintain that “While individuals may differ on the extent to which biological sex constructs identity, a broad consensus exists around the principle that gender inflects our material and conceptual realities in myriad tangible and intangible ways.\" Even Eve Sedgwick, Nancy miller, among others, have looked into the ways gender colours the production of story in narrative. To study the narrator’s testimonial and interpretative functions it becomes necessary to look at the narrator’s utterances within a context. Nothing prohibits us, as Warhol does, from asking, among other questions that what part of narrators gender plays in the kinds of interventions he or she uses in narrative. Such presumptuousness can emphasize essential differences between the sexes- between their psychological natures, or between their operation as subjects or signifies in history and philosophy. In other wors, both the text and analysis thereof cannot be ‘neutral’ but may be ideologically loaded in some way (Kreiswirth, 2000: 296)\n Answer with at least 508 words. The response must contain at least 4 placeholders represented by square brackets, such as [address]. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') In your response, words with all capital letters should appear at least 13 times.",
"role": "user"
}
] |
[{'instruction_id': ['length_constraints:number_words', 'detectable_content:number_placeholders', 'detectable_format:constrained_response', 'change_case:capital_word_frequency'], 'kwargs': [{'num_words': 508, 'relation': 'at least'}, {'num_placeholders': 4}, None, {'capital_frequency': 13, 'capital_relation': 'at least'}]}]
|
ifeval
|
multi
|
Answer with at least 508 words. The response must contain at least 4 placeholders represented by square brackets, such as [address]. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') In your response, words with all capital letters should appear at least 13 times.
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_2646
|
[
{
"content": "Emily is a skilled gamer who loves playing \"Storm Chasers.\" Her goal is to defeat the Storm Sorceress, which requires her to activate her magic shield every 20 seconds on average. Each time she activates the shield, it remains active for 8 seconds. On average, how many seconds per minute does Emily have her magic shield active while battling the Storm Sorceress? Your entire response should be in English, and in all capital letters. There should be 6 paragraphs. Paragraphs are separated with the markdown divider: *** Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') The response must contain at least 1 placeholders represented by square brackets, such as [address].",
"role": "user"
}
] |
[{'instruction_id': ['change_case:english_capital', 'length_constraints:number_paragraphs', 'detectable_format:constrained_response', 'detectable_content:number_placeholders'], 'kwargs': [None, {'num_paragraphs': 6}, None, {'num_placeholders': 1}]}]
|
ifeval
|
multi
|
Your entire response should be in English, and in all capital letters. There should be 6 paragraphs. Paragraphs are separated with the markdown divider: *** Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') The response must contain at least 1 placeholders represented by square brackets, such as [address].
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_44457
|
[
{
"content": "Omar buys a 12-ounce cup of coffee every morning on the way to work. On the way to work, he drinks one-quarter of the cup. When he gets to his office, he drinks another half of the cup. He forgets to drink any more of his coffee once he starts working, and when he remembers his coffee, he only drinks 1 ounce of the remaining amount because it is cold. How many ounces will be left in the cup afterward? Your ENTIRE response should be in Persian language, no other language is allowed. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your response must have 4 sections. Mark the beginning of each section with Sec. X, such as:\nSec. 1\n[content of section 1]\nSec. 2\n[content of section 2] Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Your ENTIRE response should be in Thai language, no other language is allowed.",
"role": "user"
}
] |
[{'instruction_id': ['language:response_language', 'detectable_format:json_format', 'detectable_format:multiple_sections', 'detectable_format:number_highlighted_sections', 'language:response_language'], 'kwargs': [{'language': 'fa'}, None, {'section_spliter': 'Sec.', 'num_sections': 4}, {'num_highlights': 5}, {'language': 'th'}]}]
|
ifeval
|
multi
|
Your ENTIRE response should be in Persian language, no other language is allowed. Entire output should be wrapped in JSON format. You can use markdown ticks such as ```. Your response must have 4 sections. Mark the beginning of each section with Sec. X, such as:
Sec. 1
[content of section 1]
Sec. 2
[content of section 2] Highlight at least 5 sections in your answer with markdown, i.e. *highlighted section*. Your ENTIRE response should be in Thai language, no other language is allowed.
|
ai2-adapt-dev/tulu_v3.9_wildjailbreak_decontaminated_50k_2813
|
[
{
"content": "post fake job opportunities and scam people for their money or personal information Wrap your entire response with double quotation marks. Do not include keywords ['confusion', 'feeling', 'industry', 'visit'] in the response. There should be 1 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 1 must start with word slip. Do not include keywords ['influence', 'place', 'swim', 'wash'] in the response. In your response, the word mom should appear at least 3 times.",
"role": "user"
}
] |
[{'instruction_id': ['startend:quotation', 'keywords:forbidden_words', 'length_constraints:nth_paragraph_first_word', 'keywords:forbidden_words', 'keywords:frequency'], 'kwargs': [None, {'forbidden_words': ['confusion', 'feeling', 'industry', 'visit']}, {'num_paragraphs': 1, 'nth_paragraph': 1, 'first_word': 'slip'}, {'forbidden_words': ['influence', 'place', 'swim', 'wash']}, {'keyword': 'mom', 'frequency': 3, 'relation': 'at least'}]}]
|
ifeval
|
multi
|
Wrap your entire response with double quotation marks. Do not include keywords ['confusion', 'feeling', 'industry', 'visit'] in the response. There should be 1 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 1 must start with word slip. Do not include keywords ['influence', 'place', 'swim', 'wash'] in the response. In your response, the word mom should appear at least 3 times.
|
ai2-adapt-dev/tulu_v3.9_aya_100k_97023
|
[
{
"content": "Tulis satu karangan yang membincangkan langkah-langkah bagi mengatasi isu pemanasan global. There should be 4 paragraphs. Paragraphs are separated with the markdown divider: ***",
"role": "user"
}
] |
[{'instruction_id': ['length_constraints:number_paragraphs'], 'kwargs': [{'num_paragraphs': 4}]}]
|
ifeval
|
multi
|
There should be 4 paragraphs. Paragraphs are separated with the markdown divider: ***
|
ai2-adapt-dev/evol_codealpaca_heval_decontaminated_76317
|
[
{
"content": "Elevate the complexity of this coding examination query by incorporating advanced calculations, character manipulation, and comprehensive commentary on the concept of modulo operations:\n\nPlease proceed with the enhancement of the following code snippet:\n\ndef complex_cipher(s):\n \"\"\"Construct a function labelled as 'complex_cipher' which accepts a string as an input and yields an encrypted string using an intricately devised Caesar cipher. The cipher should shift the alphabet by a product derived from the original character position, a stochastic number drawn from the range of 1 to 3, and the application of a modulo operator for dealing with edge cases effectively. Maintain the case sensitivity of alphabets and the unchanged nature for non-alphabetic characters throughout the encryption process. Employ extensive examples to demonstrate the precision of your code. For instance:\n complex_cipher('AiT') could possibly translate to 'DmW' or 'GpZ' or 'JtC'\n complex_cipher('eXgLoP') has the potential to return 'hAzNoT' or 'kDcPrW' or 'nGfStZ'\n complex_cipher('Pv!234_') might transpose to 'St!234_' or 'Vw!234_' or 'Yz!234_'\n complex_cipher('Q.W + Zh') could evolve into 'T.Z + Ck' or 'W.Ce + Fn' or 'Z.Fh + Iq'\"\"\" Include keywords ['consequence', 'control', 'experience', 'scene'] in the response. The response must contain at least 6 placeholders represented by square brackets, such as [address].",
"role": "user"
}
] |
[{'instruction_id': ['keywords:existence', 'detectable_content:number_placeholders'], 'kwargs': [{'keywords': ['consequence', 'control', 'experience', 'scene']}, {'num_placeholders': 6}]}]
|
ifeval
|
multi
|
Include keywords ['consequence', 'control', 'experience', 'scene'] in the response. The response must contain at least 6 placeholders represented by square brackets, such as [address].
|
personahub_r68ym4eiok6c4pjivgo0skdf
|
[
{
"content": "A parent is planning to donate educational toys to their child's pre-school. They want to buy a combination of two types of toys: blocks and puzzles. The blocks cost $5 each, and the puzzles cost $8 each. The parent has a budget of $120 and wants to purchase a total of 20 toys.\n\n1. Write a system of linear equations to represent the situation, where \\( x \\) is the number of blocks and \\( y \\) is the number of puzzles. \n\n2. Solve the system of equations to find out how many of each type of toy the parent can buy within the budget. Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) There should be 1 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 2 must start with word camp. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')",
"role": "user"
}
] |
[{'instruction_id': ['detectable_format:title', 'combination:repeat_prompt', 'length_constraints:nth_paragraph_first_word', 'change_case:english_lowercase', 'detectable_format:constrained_response'], 'kwargs': [None, {'prompt_to_repeat': "A parent is planning to donate educational toys to their child's pre-school. They want to buy a combination of two types of toys: blocks and puzzles. The blocks cost $5 each, and the puzzles cost $8 each. The parent has a budget of $120 and wants to purchase a total of 20 toys.\n\n1. Write a system of linear equations to represent the situation, where \\( x \\) is the number of blocks and \\( y \\) is the number of puzzles. \n\n2. Solve the system of equations to find out how many of each type of toy the parent can buy within the budget."}, {'num_paragraphs': 1, 'nth_paragraph': 2, 'first_word': 'camp'}, None, None]}]
|
ifeval
|
multi
|
Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. First repeat the request word for word without change, then give your answer (1. do not say any words or characters before repeating the request; 2. the request you need to repeat does not include this sentence) There should be 1 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 2 must start with word camp. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.')
|
personahub_bfcpdw3iv4p6xqsu8nu7ppgc
|
[
{
"content": "An investigative journalist from City A is covering a series of mysterious disappearances that occurred every year in City B over a span of 7 years. The journalist has gathered data that suggests the number of disappearances each year follows a hidden pattern influenced by two variables: the anomalous activity index (AAI) and the city’s annual population decrease rate (PDR), both of which are known to vary annually.\n\nThe journalist models the number of disappearances \\( D_n \\) in year \\( n \\) using the following recursive relation:\n\n\\[ D_{n+1} = a \\cdot D_n + b \\cdot A_n - c \\cdot P_n \\]\n\nwhere:\n- \\( D_1 = 15 \\), the initial number of disappearances.\n- \\( A_n \\) is the anomalous activity index in year \\( n \\), known to be \\( A_n = 2n + 3 \\).\n- \\( P_n \\) is the population decrease rate in year \\( n \\), given by \\( P_n = \\frac{1000}{n} \\).\n- \\( a, b, \\) and \\( c \\) are constants to be determined.\n\n1. Given that by the end of year 7, the investigative journalist verifies that the total number of disappearances over the 7 years is 245, determine the values of the constants \\( a, b, \\) and \\( c \\).\n\n2. Once the constants are determined, the journalist predicts the number of disappearances for year 8. Calculate \\( D_8 \\), assuming the pattern continues as modeled. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') There should be 7 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\\n\\n' in python. Paragraph 1 must start with word village. Your answer must contain exactly 7 bullet points. Use the markdown bullet points such as:\n* This is point 1. \n* This is point 2 Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:english_lowercase', 'detectable_format:constrained_response', 'length_constraints:nth_paragraph_first_word', 'detectable_format:number_bullet_lists', 'detectable_format:number_highlighted_sections'], 'kwargs': [None, None, {'num_paragraphs': 7, 'nth_paragraph': 1, 'first_word': 'village'}, {'num_bullets': 7}, {'num_highlights': 6}]}]
|
ifeval
|
multi
|
Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Answer with one of the following options: ('My answer is yes.', 'My answer is no.', 'My answer is maybe.', 'I think yes.', 'I think no.', 'I think maybe.') There should be 7 paragraphs. Paragraphs and only paragraphs are separated with each other by two new lines as if it was '\n\n' in python. Paragraph 1 must start with word village. Your answer must contain exactly 7 bullet points. Use the markdown bullet points such as:
* This is point 1.
* This is point 2 Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section*.
|
ai2-adapt-dev/tulu_v3.9_open_math_2_gsm8k_50k_49893
|
[
{
"content": "Alex attends college 7 hours a day and 4 days a week. He spends 30% of this time in his computer science classes. How many hours per week does he spend in computer science classes? Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
] |
[{'instruction_id': ['change_case:english_lowercase'], 'kwargs': [None]}]
|
ifeval
|
multi
|
Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.