@inproceedings{shen-etal-2023-loose,
    title = "Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback",
    author = "Shen, Wei  and
      Zheng, Rui  and
      Zhan, Wenyu  and
      Zhao, Jun  and
      Dou, Shihan  and
      Gui, Tao  and
      Zhang, Qi  and
      Huang, Xuanjing",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.findings-emnlp.188/",
    doi = "10.18653/v1/2023.findings-emnlp.188",
    pages = "2859--2873"
}