RU, Y.; HUANG, Y.; ZHANG, X. RMO: Towards Better LLM Alignment via Reshaping Reward Margin Distributions. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 39, p. 32851-32859, 2026. DOI: 10.1609/aaai.v40i39.40565. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40565. Acesso em: 4 may. 2026.