@inproceedings{wang-etal-2024-reward,
    title = "Reward Difference Optimization For Sample Reweighting In Offline {RLHF}",
    author = "Wang, Shiqi  and
      Zhang, Zhengze  and
      Zhao, Rui  and
      Tan, Fei  and
      Cam-Tu, Nguyen",
    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/jlcl-multiple-ingestion/2024.findings-emnlp.115/",
    doi = "10.18653/v1/2024.findings-emnlp.115",
    pages = "2109--2123"
}