@inproceedings{xu-etal-2024-bpo,
    title = "{BPO}: Staying Close to the Behavior {LLM} Creates Better Online {LLM} Alignment",
    author = "Xu, Wenda  and
      Li, Jiachen  and
      Wang, William Yang  and
      Li, 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/fix-sig-urls/2024.emnlp-main.623/",
    doi = "10.18653/v1/2024.emnlp-main.623",
    pages = "11125--11139"
}