@inproceedings{lin-etal-2024-limited,
    title = "On the Limited Generalization Capability of the Implicit Reward Model Induced by Direct Preference Optimization",
    author = "Lin, Yong  and
      Seto, Skyler  and
      Ter Hoeve, Maartje  and
      Metcalf, Katherine  and
      Theobald, Barry-John  and
      Wang, Xuan  and
      Zhang, Yizhe  and
      Huang, Chen  and
      Zhang, Tong",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-emnlp.940/",
    doi = "10.18653/v1/2024.findings-emnlp.940",
    pages = "16015--16026"
}