Course-Correction: Safety Alignment Using Synthetic Preferences Rongwu Xu author Yishuo Cai author Zhenhong Zhou author Renjie Gu author Haiqin Weng author Liu Yan author Tianwei Zhang author Wei Xu author Han Qiu author 2024-11 text Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track Franck Dernoncourt editor Daniel Preoţiuc-Pietro editor Anastasia Shimorina editor Association for Computational Linguistics Miami, Florida, US conference publication xu-etal-2024-course 10.18653/v1/2024.emnlp-industry.119 https://aclanthology.org/2024.emnlp-industry.119/ 2024-11 1622 1649