@inproceedings{zhang-etal-2025-safety, title = "Safety is Not Only About Refusal: Reasoning-Enhanced Fine-tuning for Interpretable {LLM} Safety", author = "Zhang, Yuyou and Li, Miao and Han, William and Yao, Yihang and Cen, Zhepeng and Zhao, Ding", 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.960/", pages = "18727--18746", ISBN = "979-8-89176-256-5" }