@inproceedings{bao-etal-2025-fixing,
    title = "Fixing Distribution Shifts of {LLM} Self-Critique via On-Policy Self-Play Training",
    author = "Bao, Rong  and
      Yu, Donglei  and
      Fan, Kai  and
      Liao, Minpeng",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.acl-long.865/",
    pages = "17680--17700",
    ISBN = "979-8-89176-251-0"
}