@inproceedings{ye-etal-2025-improving,
    title = "Improving Reward Models with Synthetic Critiques",
    author = "Ye, Zihuiwen  and
      Greenlee, Fraser David  and
      Bartolo, Max  and
      Blunsom, Phil  and
      Campos, Jon Ander  and
      Gall{\'e}, Matthias",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2025.findings-naacl.254/",
    doi = "10.18653/v1/2025.findings-naacl.254",
    pages = "4506--4520",
    ISBN = "979-8-89176-195-7"
}