Xingyu Lin, Yilin Wen 0007, Du Su, En Wang, Wenbin Liu, Zhonghou Lv, Jinchang Hou, Chenfu Bao. Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 32256-32269, Association for Computational Linguistics, 2026. [doi]
Abstract is missing.