BPO: Staying Close to the Behavior LLM Creates Better Online LLM Alignment Wenda Xu author Jiachen Li author William Yang Wang author Lei Li author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing Yaser Al-Onaizan editor Mohit Bansal editor Yun-Nung Chen editor Association for Computational Linguistics Miami, Florida, USA conference publication xu-etal-2024-bpo 10.18653/v1/2024.emnlp-main.623 https://aclanthology.org/2024.emnlp-main.623/ 2024-11 11125 11139