@inproceedings{wu-2025-comprehensive,
    title = "A Comprehensive Survey on Learning from Rewards for Large Language Models: Reward Models and Learning Strategies",
    author = "Wu, Xiaobao",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/name-variant-enfa-fane/2025.findings-emnlp.970/",
    doi = "10.18653/v1/2025.findings-emnlp.970",
    pages = "17847--17875",
    ISBN = "979-8-89176-335-7"
}