@inproceedings{zhang-etal-2025-copr,
    title = "{COPR}: Continual Human Preference Learning via Optimal Policy Regularization",
    author = "Zhang, Han  and
      Gui, Lin  and
      Lei, Yu  and
      Zhai, Yuanzhao  and
      Zhang, Yehong  and
      Zhang, Zhuo  and
      He, Yulan  and
      Wang, Hui  and
      Yu, Yue  and
      Wong, Kam-Fai  and
      Liang, Bin  and
      Xu, Ruifeng",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.findings-acl.281/",
    doi = "10.18653/v1/2025.findings-acl.281",
    pages = "5377--5398",
    ISBN = "979-8-89176-256-5"
}