TIAN, Changyuan et al. Rectify Evaluation Preference: Improving LLMs’ Critique on Math Reasoning via Perplexity-aware Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 39, p. 33241–33249, 2026. DOI: 10.1609/aaai.v40i39.40609. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40609. Acesso em: 15 may. 2026.