@inproceedings{wang-etal-2024-reward-modeling,
    title = "Reward Modeling Requires Automatic Adjustment Based on Data Quality",
    author = "Wang, Binghai  and
      Zheng, Rui  and
      Chen, Lu  and
      Xi, Zhiheng  and
      Shen, Wei  and
      Zhou, Yuhao  and
      Yan, Dong  and
      Gui, Tao  and
      Zhang, Qi  and
      Huang, Xuanjing",
    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.234/",
    doi = "10.18653/v1/2024.findings-emnlp.234",
    pages = "4041--4064"
}