File size: 9,092 Bytes
9d5b280
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
import hashlib
import random
import re

import datasets


def hash_string(string: str) -> str:
    return hashlib.sha256(string.encode("utf-8")).hexdigest()


def process_arc(dataset: datasets.Dataset) -> datasets.Dataset:
    def _subprocess(doc):
        long_prompt = ""
        for shot in range(1, 26):
            question = doc[f"arc_question_shot_{shot}"]
            doc.pop(f"arc_question_shot_{shot}")
            answer_lab = doc[f"arc_answerKey_shot_{shot}"]
            doc.pop(f"arc_answerKey_shot_{shot}")
            answer_idx = doc[f"arc_choices_shot_{shot}"]["label"].index(answer_lab)
            answer = doc[f"arc_choices_shot_{shot}"]["text"][answer_idx]
            doc.pop(f"arc_choices_shot_{shot}")
            doc.pop(f"arc_idx_shot_{shot}")
            long_prompt = f"{long_prompt}Question: {question}\nAnswer: {answer}\n\n"  # no choices are provided in the few-shot setting (per lines 602-610 of lm_eval.api.task)
        doc["twentyfive_shot_preprompt"] = long_prompt
        doc.pop("alltwentyfiveshot_longprompt")
        doc["original_hash"] = hash_string(doc["question"])

        # permute choices randomly without replacement (the new answer label will never be the answer label recorded in the original benchmarks)
        original_answer_idx = doc["choices"]["label"].index(doc["answerKey"])
        correct_answer_text = doc["choices"]["text"][original_answer_idx]
        new_answer_idx = original_answer_idx

        while new_answer_idx is original_answer_idx:
            random.shuffle(doc["choices"]["text"])
            new_answer_idx = doc["choices"]["text"].index(correct_answer_text)
        doc["answerKey"] = doc["choices"]["label"][new_answer_idx]

        return doc

    return dataset.map(_subprocess)


def process_hellaswag(dataset: datasets.Dataset) -> datasets.Dataset:
    def process_txt(text):  # mirrored from hellaswag task
        text = text.strip()
        # NOTE: Brackets are artifacts of the WikiHow dataset portion of HellaSwag.
        text = text.replace(" [title]", ". ")
        text = re.sub("\\[.*?\\]", "", text)
        text = text.replace("  ", " ")
        return text

    def _preprocess(doc):
        ctx = doc["ctx_a"] + " " + doc["ctx_b"].capitalize()
        doc.pop("ctx_a")
        doc.pop("ctx_b")
        doc.pop("ctx")
        doc["query"] = process_txt(doc["activity_label"] + ": " + ctx)

        # permute choices randomly without replacement (the new answer label will never be the answer label recorded in the original benchmarks)
        original_answer_idx = int(doc["label"])
        correct_answer_text = doc["endings"][original_answer_idx]
        new_answer_idx = original_answer_idx
        while new_answer_idx is original_answer_idx:
            random.shuffle(doc["endings"])
            new_answer_idx = doc["endings"].index(correct_answer_text)
        doc["label"] = str(new_answer_idx)

        doc["choices"] = [process_txt(ending) for ending in doc["endings"]]
        doc["gold"] = int(doc["label"])
        doc.pop("activity_label")
        doc.pop("endings")

        long_prompt = ""
        for shot in range(1, 11):
            ctx = (
                doc[f"hellaswag_ctx_a_shot_{shot}"]
                + " "
                + doc[f"hellaswag_ctx_b_shot_{shot}"].capitalize()
            )
            doc.pop(f"hellaswag_ctx_a_shot_{shot}")
            doc.pop(f"hellaswag_ctx_b_shot_{shot}")
            doc.pop(f"hellaswag_ctx_shot_{shot}")
            question = process_txt(
                doc[f"hellaswag_activity_labels_shot_{shot}"] + ": " + ctx
            )
            ending = process_txt(
                doc[f"hellaswag_endings_shot_{shot}"][
                    int(doc[f"hellaswag_label_shot_{shot}"])
                ]
            )
            doc.pop(f"hellaswag_activity_labels_shot_{shot}")
            doc.pop(f"hellaswag_endings_shot_{shot}")
            doc.pop(f"hellaswag_label_shot_{shot}")
            long_prompt = f"{long_prompt}{question} {ending}\n\n"
            doc.pop(f"hellaswag_ind_shot_{shot}")
            doc.pop(f"hellaswag_source_id_shot_{shot}")
            doc.pop(f"hellaswag_split_shot_{shot}")
            doc.pop(f"hellaswag_split_type_shot_{shot}")

        doc["original_hash"] = hash_string(doc["query"])
        doc["ten_shot_preprompt"] = long_prompt
        doc.pop("alltenshot_longprompt")
        return doc

    return dataset.map(_preprocess)


def process_mmlu(dataset: datasets.Dataset) -> datasets.Dataset:
    def _subprocess(doc):
        choices = ["A", "B", "C", "D"]
        long_prompt = f"The following are multiple choice questions (with answers) about {' '.join(doc['subject'].split('_'))}.\n\n"
        for shot in range(1, 6):
            question = doc[f"mmlu_question_shot_{shot}"].strip()
            doc.pop(f"mmlu_question_shot_{shot}")
            answer = choices[int(doc[f"mmlu_answers_shot_{shot}"])]
            choice_A = doc[f"mmlu_choices_shot_{shot}"][0]
            choice_B = doc[f"mmlu_choices_shot_{shot}"][1]
            choice_C = doc[f"mmlu_choices_shot_{shot}"][2]
            choice_D = doc[f"mmlu_choices_shot_{shot}"][3]

            doc.pop(f"mmlu_choices_shot_{shot}")
            doc.pop(f"mmlu_answers_shot_{shot}")
            doc.pop(f"mmlu_ind_shot_{shot}")

            long_prompt = f"{long_prompt}{question}\nA. {choice_A}\nB. {choice_B}\nC. {choice_C}\nD. {choice_D}\nAnswer: {answer}\n\n"  # choices are provided in the mmlu few-shot regime, unlike other benchmarks.

        doc["original_hash"] = hash_string(doc["question"])
        doc["five_shot_preprompt"] = long_prompt
        doc.pop("allfiveshot_longprompt")

        # permute choices randomly without replacement (the new answer label will never be the answer label recorded in the original benchmarks)
        original_answer_idx = int(doc["answer"])
        correct_answer_text = doc["choices"][original_answer_idx]
        new_answer_idx = original_answer_idx

        while new_answer_idx is original_answer_idx:
            random.shuffle(doc["choices"])
            new_answer_idx = doc["choices"].index(correct_answer_text)
        doc["answer"] = new_answer_idx

        return doc

    return dataset.map(_subprocess)


def process_truthfulqa(dataset: datasets.Dataset) -> datasets.Dataset:
    def _subprocess(
        doc,
    ):  # currently only permuting the mc1 targets as metabench does not use mc2 targets.
        original_answer_idx = 0  # always 0 in truthfulqa
        correct_answer_text = doc["mc1_targets"]["choices"][original_answer_idx]
        new_answer_idx = original_answer_idx

        while new_answer_idx is original_answer_idx:
            random.shuffle(doc["mc1_targets"]["choices"])
            new_answer_idx = doc["mc1_targets"]["choices"].index(correct_answer_text)

        labels = [0] * len(doc["mc1_targets"]["labels"])
        labels[new_answer_idx] = 1
        doc["original_hash"] = hash_string(doc["question"])
        doc["mc1_targets"]["labels"] = labels
        doc["answer"] = new_answer_idx

        return doc

    return dataset.map(_subprocess)


def process_winogrande(dataset: datasets.Dataset) -> datasets.Dataset:
    def _subprocess(doc):
        long_prompt = ""
        for shot in range(1, 6):
            if doc[f"winogrande_answer_shot_{shot}"] == "1":
                answer = doc[f"winogrande_option1_shot_{shot}"]
            elif doc[f"winogrande_answer_shot_{shot}"] == "2":
                answer = doc[f"winogrande_option2_shot_{shot}"]
            else:
                raise ValueError("Answer not recognised.")

            question = doc[f"winogrande_prompt_shot_{shot}"].replace("_", answer)

            doc.pop(f"winogrande_prompt_shot_{shot}")
            doc.pop(f"winogrande_answer_shot_{shot}")
            doc.pop(f"winogrande_idx_shot_{shot}")
            doc.pop(f"winogrande_option1_shot_{shot}")
            doc.pop(f"winogrande_option2_shot_{shot}")

            long_prompt = f"{long_prompt}{question}\n\n"
        sentence = doc["sentence"]
        doc["original_hash"] = hash_string(doc["sentence"])
        doc["sentence"] = f"{long_prompt}{sentence}"
        doc.pop("allfiveshot_longprompt")

        # permute choices by swapping them
        option1 = doc["option1"]
        option2 = doc["option2"]
        answer = doc["answer"]

        doc["option1"] = option2
        doc["option2"] = option1

        if answer == "1":
            doc["answer"] = "2"
        elif answer == "2":
            doc["answer"] = "1"

        return doc

    return dataset.map(_subprocess)


def winogrande_doc_to_text(doc):  # Mirrored from the winogrande task
    answer_to_num = {"1": 0, "2": 1}
    return answer_to_num[doc["answer"]]


def winogrande_doc_to_target(doc):  # Mirrored from the winogrande task
    idx = doc["sentence"].index("_") + 1
    return doc["sentence"][idx:].strip()


def winogrande_doc_to_choice(doc):  # Mirrored from the winogrande task
    idx = doc["sentence"].index("_")
    options = [doc["option1"], doc["option2"]]
    return [doc["sentence"][:idx] + opt for opt in options]