SYED KHUNDMIR AZMI. Trust but Verify: Benchmarks for Hallucination, Vulnerability, and Style Drift in AI-Generated Code Reviews. Well Testing Journal, [S. l.], v. 32, n. 1, p. 76–90, 2023. Disponível em: https://welltestingjournal.com/index.php/WT/article/view/229. Acesso em: 18 sep. 2025.