XUANYI FU; 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, [S. l.], v. 6, n. 3, p. 34–45, 2025. DOI: 10.69987/. Disponível em: https://learnedvertex.com/index.php/JAIR/article/view/361. Acesso em: 10 oct. 2026.