@inproceedings{siu-etal-2025-cosmic, title = "{COSMIC}: Generalized Refusal Direction Identification in {LLM} Activations", author = "Siu, Vincent and Crispino, Nicholas and Yu, Zihao and Pan, Sam and Wang, Zhun and Liu, Yang and Song, Dawn and Wang, Chenguang", editor = "Che, Wanxiang and Nabende, Joyce and Shutova, Ekaterina and Pilehvar, Mohammad Taher", booktitle = "Findings of the Association for Computational Linguistics: ACL 2025", month = jul, year = "2025", address = "Vienna, Austria", publisher = "Association for Computational Linguistics", url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.1310/", pages = "25534--25553", ISBN = "979-8-89176-256-5" }