@inproceedings{lang-etal-2024-fine,
    title = "Fine-Tuning Language Models with Reward Learning on Policy",
    author = "Lang, Hao  and
      Huang, Fei  and
      Li, Yongbin",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2024.naacl-long.75/",
    doi = "10.18653/v1/2024.naacl-long.75",
    pages = "1382--1392"
}