@inproceedings{zhou-etal-2024-reflect,
    title = "Reflect-{RL}: Two-Player Online {RL} Fine-Tuning for {LM}s",
    author = "Zhou, Runlong  and
      Du, Simon  and
      Li, Beibin",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.acl-long.56/",
    doi = "10.18653/v1/2024.acl-long.56",
    pages = "995--1015"
}