Xuanyi Fu, and Danbing Zou. “A Comparative Empirical Study of Over-Refusal Behavior in Closed-Source Large Language Models on Pseudo-Harmful Prompts”. Journal of Artificial Intelligence Review 6, no. 3 (July 10, 2025): 34–45. Accessed October 10, 2026. https://learnedvertex.com/index.php/JAIR/article/view/361.