Tian, Changyuan, Zhicong Lu, Shuang Qian, Nayu Liu, Peiguang Li, Li Jin, Leiyi Hu, et al. “Rectify Evaluation Preference: Improving LLMs’ Critique on Math Reasoning via Perplexity-Aware Reinforcement Learning”. Proceedings of the AAAI Conference on Artificial Intelligence 40, no. 39 (March 14, 2026): 33241–33249. Accessed May 15, 2026. https://ojs.aaai.org/index.php/AAAI/article/view/40609.