@inproceedings{quan-2024-dmoerm,
    title = "{DM}o{ERM}: Recipes of Mixture-of-Experts for Effective Reward Modeling",
    author = "Quan, Shanghaoran",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2024.findings-acl.418/",
    doi = "10.18653/v1/2024.findings-acl.418",
    pages = "7006--7028"
}