@inproceedings{cao-etal-2024-enhancing,
    title = "Enhancing Reinforcement Learning with Dense Rewards from Language Model Critic",
    author = "Cao, Meng  and
      Shu, Lei  and
      Yu, Lei  and
      Zhu, Yun  and
      Wichers, Nevan  and
      Liu, Yinxiao  and
      Meng, Lei",
    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/Author-page-Marten-During-lu/2024.emnlp-main.515/",
    doi = "10.18653/v1/2024.emnlp-main.515",
    pages = "9119--9138"
}