Alignment-Enhanced Decoding: Defending Jailbreaks via Token-Level Adaptive Refining of Probability Distributions Quan Liu author Zhenhong Zhou author Longzhu He author Yi Liu author Wei Zhang author Sen Su 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 liu-etal-2024-alignment 10.18653/v1/2024.emnlp-main.164 https://aclanthology.org/2024.emnlp-main.164/ 2024-11 2802 2816