Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate

Yubo Wang, Xiang Yue, Wenhu Chen

Keywords: Reasoning, Large Language Model, Fine-Tuning

TL;DR: We introduce Critique Fine-Tuning, a training method that teaches LM to critique responses, achieving better performance than SFT with fewer training samples and comparable results to RL methods.

Abstract: Supervised Fine-Tuning (SFT) is commonly used to train language models to imitate annotated responses for given instructions. In this paper, we propose Critique Fine-Tuning (CFT), a method more effective than SFT for reasoning tasks. Instead of simply imitating correct responses, CFT trains models to critique noisy responses, inspired by human learning processes that emphasize critical thinking, deeper analysis, and nuanced understanding--traits often overlooked by standard SFT. To validate the effectiveness of CFT, we construct multiple critique datasets (e.g., WebInstruct, MetaMath, NuminaMath), where GPT-4o serves as the teacher to generate critiques in the form of ([query; noisy response], critique). Experiments on these datasets demonstrate that CFT consistently outperforms SFT by 4--10% across six mathematical reasoning benchmarks, and is effective across different base models including Qwen2.5, Qwen2.5-Math, and DeepSeek-Math. Notably, our model Qwen2.5-Math-CFT only requires 1 hour of training on 8xH100 over the 50K examples, yet matches or outperforms strong competitors like Qwen2.5-Math-Instruct on most benchmarks, which use over 2M samples. Moreover, it matches the performance of SimpleRL, which is a DeepSeek-r1 replication trained with 140x more compute. Experiments on IF_Eval and MT-Bench further demonstrate that CFT can significantly enhance the model's general generation and instruction-following capabilities, outperforming the Qwen2.5-Math-Instruct by a large margin. Ablation studies show that CFT is robust to noisy response sources and teacher critique models. These findings highlight that CFT offers a more effective alternative to advance the reasoning of language models.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the COLM Code of Ethics on https://colmweb.org/CoE.html

Author Guide: I certify that this submission complies with the submission instructions as described on https://colmweb.org/AuthorGuide.html

Submission Number: 926