@inproceedings{lin-etal-2026-token,
    title = "Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via sequence-level likelihood",
    author = "Lin, Xingyu  and
      Wen, Yilin  and
      Su, Du  and
      Wang, En  and
      Liu, Wenbin  and
      Lv, Zhonghou  and
      Hou, Jinchang  and
      Bao, Chenfu",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1488/",
    pages = "32256--32269",
    ISBN = "979-8-89176-390-6"
}