Chen Z, Liu F, Zhu X, Wang H, Li J, Qi Y, et al. Preference Optimization via Contrastive Divergence: Your Policy Is Secretly an NLL Estimator. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 14];40(44):37286-94. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/41060