PAN, Junshu; SHEN, Wei; HUANG, Shulin; ZHOU, Qiji; ZHANG, Yue. Pre-DPO: Improving Data Utilization in Direct Preference Optimization Using a Guiding Reference Model. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 38, p. 32646–32654, 2026. DOI: 10.1609/aaai.v40i38.40542. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40542. Acesso em: 14 may. 2026.