Modelpublic

TIGER-Lab/One-Shot-CFT-Math-Qwen-1.5B

sourceHugging Facecc-by-4.0updated 1y agoView on Hugging Face

0likes14downloads

Model Card

One-Shot-CFT: Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem

<a href="https://github.com/TIGER-AI-Lab/One-Shot-CFT" target="blank">💻 Code</a> | <a href="https://arxiv.org/pdf/2506.03295" target="blank">📄 Paper</a> | <a href="https://huggingface.co/datasets/TIGER-Lab/One-Shot-CFT-Data" target="blank">📊 Dataset</a> | <a href="https://huggingface.co/collections/TIGER-Lab/one-shot-cft-683fbb4d2bcf698dbea8fb21" target="blank">🤗 Model</a> | <a href="https://tiger-ai-lab.github.io/One-Shot-CFT/" target="_blank">🌐 Project Page</a>

🧠 Overview

One-Shot Critique Fine-Tuning (CFT) is a simple, robust, and compute-efficient training paradigm for unleashing the reasoning capabilities of pretrained LLMs in both mathematical and logical domains. By leveraging critiques on just one problem, One-Shot CFT enables models like Qwen and LLaMA to match or even outperform reinforcement learning, while using 20× less compute.

Instead of learning from reference answers (as in supervised fine-tuning) or reward signals (as in reinforcement learning), One-Shot CFT enables models to learn from critiques of diverse solutions to a single problem, enhancing their exposure to varied reasoning patterns and mitigating overfitting. This exposes the LLMs to multiple perspectives and error types, thereby more effectively unleashing their reasoning potential.

✨ Key Highlights

—Unleashes Reasoning with One Example: One-Shot CFT uses critiques of diverse model-generated solutions to a single problem to significantly boost performance across math and logic tasks. For example, with just 5 GPU hours of training on Qwen2.5-Math-7B, One-Shot CFT achieves an average improvement of +15% on six math benchmarks and +16% on three logic reasoning benchmarks.
—Outperforms RLVR and Full SFT with 20× Less Compute: One-Shot CFT outperforms both one-shot Reinforcement Learning with Verifiable Rewards (RLVR) and full-dataset supervised fine-tuning, while requiring only 5 GPU hours on a 7B model—offering a much more efficient and stable training alternative.
—Robust Across Seeds and Model Scales: One-Shot CFT remains effective across different seed problem choices and model sizes—from 1.5B to 14B parameters—demonstrating strong generalization and scalability.

This specific model is the One-Shot CFT variant trained based on [Qwen2.5-1.5B-Math](https://huggingface.co/Qwen/Qwen2.5-Math-1.5B) with [DSR-CFT-p0](https://huggingface.co/datasets/TIGER-Lab/One-Shot-CFT-Data) dataset.

Main Results

One-shot CFT consistently improves mathematical and logical reasoning. Left: Average accuracy on six mathematical reasoning benchmarks for Qwen and LLaMA models, comparing base, SFT, RLVR, and CFT with only one training example. Right: In-domain accuracy on three logic reasoning benchmarks (BBEH subtasks) for Qwen2.5-Math-7B. Across both domains, CFT with a single problem significantly outperforms standard SFT and matches or exceeds reinforcement learning with much lower compute.

Citation

If you find our work helpful, please cite it as:

bibtex

@article{wang2025unleashing,
  title={Unleashing the Reasoning Potential of Pre-trained LLMs by Critique Fine-Tuning on One Problem},
  author={Wang, Yubo and Nie, Ping and Zou, Kai and Wu, Lijun and Chen, Wenhu},
  journal={arXiv preprint arXiv:2506.03295},
  year={2025}
}