@inproceedings{lin-etal-2024-navigating-noisy,
    title = "Navigating Noisy Feedback: Enhancing Reinforcement Learning with Error-Prone Language Models",
    author = "Lin, Muhan  and
      Shi, Shuyang  and
      Guo, Yue  and
      Chalaki, Behdad  and
      Tadiparthi, Vaishnav  and
      Moradi Pari, Ehsan  and
      Stepputtis, Simon  and
      Campbell, Joseph  and
      Sycara, Katia P.",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-emnlp.939/",
    doi = "10.18653/v1/2024.findings-emnlp.939",
    pages = "16002--16014"
}