@inproceedings{zhou-etal-2024-wpo,
    title = "{WPO}: Enhancing {RLHF} with Weighted Preference Optimization",
    author = "Zhou, Wenxuan  and
      Agrawal, Ravi  and
      Zhang, Shujian  and
      Indurthi, Sathish Reddy  and
      Zhao, Sanqiang  and
      Song, Kaiqiang  and
      Xu, Silei  and
      Zhu, Chenguang",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.475/",
    doi = "10.18653/v1/2024.emnlp-main.475",
    pages = "8328--8340"
}