@inproceedings{lu-etal-2024-eliminating,
    title = "Eliminating Biased Length Reliance of Direct Preference Optimization via Down-Sampled {KL} Divergence",
    author = "Lu, Junru  and
      Li, Jiazheng  and
      An, Siyu  and
      Zhao, Meng  and
      He, Yulan  and
      Yin, Di  and
      Sun, Xing",
    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://aclanthology.org/2024.emnlp-main.60/",
    doi = "10.18653/v1/2024.emnlp-main.60",
    pages = "1047--1067"
}