1.
Cao Z, Yang Y, Zhao H. SCANS: Mitigating the Exaggerated Safety for LLMs via Safety-Conscious Activation Steering. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 10];39(22):23523-31. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/34521