71 lines
2.6 KiB
Markdown
71 lines
2.6 KiB
Markdown
|
---
|
||
|
|
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
|
||
|
|
|
||
|
|
## Overview
|
||
|
|
|
||
|
|
**TutorRL-7B** 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
|
||
|
|
|
||
|
|
## Example Usage
|
||
|
|
|
||
|
|
```python
|
||
|
|
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||
|
|
|
||
|
|
model_id = "eth-nlped/TutorRL-7B"
|
||
|
|
|
||
|
|
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))
|
||
|
|
```
|
||
|
|
|
||
|
|
> Note: This model does **not** generate `<think>` blocks. If you want planning-based reasoning, refer to this model variant: [TutorRL-7B-think](https://huggingface.co/eth-nlped/TutorRL-7B-think)
|
||
|
|
|
||
|
|
## 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}
|
||
|
|
}
|
||
|
|
```
|