The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness Neeraj Varshney author Pavel Dolin author Agastya Seth author Chitta Baral author 2024-08 text Findings of the Association for Computational Linguistics: ACL 2024 Lun-Wei Ku editor Andre Martins editor Vivek Srikumar editor Association for Computational Linguistics Bangkok, Thailand conference publication varshney-etal-2024-art 10.18653/v1/2024.findings-acl.776 https://aclanthology.org/2024.findings-acl.776/ 2024-08 13111 13128