@inproceedings{lee-lim-2024-towards,
    title = "Towards {P}areto-Efficient {RLHF}: Paying Attention to a Few High-Reward Samples with Reward Dropout",
    author = "Lee, Changhun  and
      Lim, Chiehyeon",
    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.489/",
    doi = "10.18653/v1/2024.findings-emnlp.489",
    pages = "8335--8349"
}