@inproceedings{ma-etal-2025-s2r,
    title = "{S}$^2${R}: Teaching {LLM}s to Self-verify and Self-correct via Reinforcement Learning",
    author = "Ma, Ruotian  and
      Wang, Peisong  and
      Liu, Cheng  and
      Liu, Xingyan  and
      Chen, Jiaqi  and
      Zhang, Bang  and
      Zhou, Xin  and
      Du, Nan  and
      Li, Jia",
    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/landing_page/2025.acl-long.1104/",
    pages = "22632--22654",
    ISBN = "979-8-89176-251-0"
}