|
|
--- |
|
|
library_name: transformers |
|
|
license: apache-2.0 |
|
|
license_link: https://github.com/eth-lre/PedagogicalRL/blob/main/LICENSE |
|
|
pipeline_tag: text-generation |
|
|
base_model: |
|
|
- Qwen/Qwen2.5-7B-Instruct |
|
|
tags: |
|
|
- math-tutor |
|
|
- grpo |
|
|
datasets: |
|
|
- SynthLabsAI/Big-Math-RL-Verified |
|
|
--- |
|
|
|
|
|
# TutorRL-7B-think |
|
|
|
|
|
## Overview |
|
|
|
|
|
**TutorRL-7B-think** is a fine-tuned variant of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct), trained to act as a math **tutor** rather than a solver. It is aligned to pedagogical principles using **reinforcement learning (GRPO)** in a synthetic multi-turn classroom setting, without requiring any human-labeled data. |
|
|
|
|
|
This model was developed as part of the research project [*From Problem-Solving to Teaching Problem-Solving*](https://arxiv.org/abs/2505.15607), which proposes a scalable, annotation-free approach to training LLMs as **educational tutors**. Instead of directly answering questions, the model is optimized to scaffold reasoning, guide through Socratic questioning, and withhold final solutions when beneficial for learning. |
|
|
|
|
|
Repository: [https://github.com/eth-lre/PedagogicalRL](https://github.com/eth-lre/PedagogicalRL) |
|
|
|
|
|
## Intended Use |
|
|
|
|
|
This model is intended for use in: |
|
|
|
|
|
* Interactive math tutoring |
|
|
* Socratic dialogue generation |
|
|
* Research on educational alignment of LLMs |
|
|
* Safe and indirect teaching in problem-solving contexts |
|
|
|
|
|
## Thinking |
|
|
This model variant allows for hidden thinking. |
|
|
The thinking content is enclosed in tags: `<think> ... </think>`. |
|
|
|
|
|
## Example Usage |
|
|
|
|
|
```python |
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM |
|
|
|
|
|
model_id = "eth-nlped/TutorRL-7B-think" |
|
|
|
|
|
tokenizer = AutoTokenizer.from_pretrained(model_id) |
|
|
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto") |
|
|
|
|
|
messages = [ |
|
|
{"role": "user", "content": "Can you help me solve 3x + 5 = 20?"} |
|
|
] |
|
|
|
|
|
prompt = tokenizer.apply_chat_template(messages, tokenize=False) |
|
|
inputs = tokenizer(prompt, return_tensors="pt").to(model.device) |
|
|
|
|
|
outputs = model.generate(**inputs, max_new_tokens=512) |
|
|
print(tokenizer.decode(outputs[0], skip_special_tokens=True)) |
|
|
``` |
|
|
|
|
|
## Citation |
|
|
|
|
|
If you use this model or build upon the training framework, please cite: |
|
|
|
|
|
``` |
|
|
@misc{dinucujianu2025problemsolvingteachingproblemsolvingaligning, |
|
|
title={From Problem-Solving to Teaching Problem-Solving: Aligning LLMs with Pedagogy using Reinforcement Learning}, |
|
|
author={David Dinucu-Jianu and Jakub Macina and Nico Daheim and Ido Hakimi and Iryna Gurevych and Mrinmaya Sachan}, |
|
|
year={2025}, |
|
|
eprint={2505.15607}, |
|
|
archivePrefix={arXiv}, |
|
|
primaryClass={cs.CL}, |
|
|
url={https://arxiv.org/abs/2505.15607} |
|
|
} |
|
|
``` |
