LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback
Gao, Bofei, Cai, Zefan, Xu, Runxin, Wang, Peiyi, Zheng, Ce, Lin, Runji, Lu, Keming, Liu, Dayiheng, Zhou, Chang, Xiao, Wen, Hu, Junjie, Liu, Tianyu, Chang, Baobao
–arXiv.org Artificial Intelligence
Mathematical verfier achieves success in mathematical reasoning tasks by validating the correctness of solutions. However, existing verifiers are trained with binary classification labels, which are not informative enough for the model to accurately assess the solutions. To mitigate the aforementioned insufficiency of binary labels, we introduce step-wise natural language feedbacks as rationale labels (i.e., the correctness of the current step and the explanations). In this paper, we propose \textbf{Math-Minos}, a natural language feedback enhanced verifier by constructing automatically-generated training data and a two-stage training paradigm for effective training and efficient inference. Our experiments reveal that a small set (30k) of natural language feedbacks can significantly boost the performance of the verifier by the accuracy of 1.6\% (86.6\% $\rightarrow$ 88.2\%) on GSM8K and 0.8\% (37.8\% $\rightarrow$ 38.6\%) on MATH. We have released our code and data for further exploration.
arXiv.org Artificial Intelligence
Jul-8-2024
- Country:
- North America
- Canada (0.14)
- United States > Wisconsin (0.14)
- North America
- Genre:
- Research Report (0.50)
- Technology: