Rectify Evaluation Preference: Improving LLMs' Critique on Math Reasoning via Perplexity-aware Reinforcement Learning.

Changyuan Tian, Zhicong Lu, Shuang Qian, Nayu Liu, Peiguang Li, Li Jin, Leiyi Hu, Zhizhao Zeng, Sirui Wang, Ke Zeng, Guozhi Cas

Browse the full AAAI paper archive.