@inproceedings{li-etal-2024-optimizing-language,
    title = "Optimizing Language Models with Fair and Stable Reward Composition in Reinforcement Learning",
    author = "Li, Jiahui  and
      Zhang, Hanlin  and
      Zhang, Fengda  and
      Chang, Tai-Wei  and
      Kuang, Kun  and
      Chen, Long  and
      Zhou, Jun",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.emnlp-main.565/",
    doi = "10.18653/v1/2024.emnlp-main.565",
    pages = "10122--10140"
}