Xiaohao Luo, Ying Wei, Rui Zhao. Detecting What Queries Seek: Steering LLM Safety with FFN Output Activation Monitoring. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 29500-29514, Association for Computational Linguistics, 2026. [doi]
Abstract is missing.