GUEORGUIEVA, Anna-Maria; CALISKAN, Aylin. Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 44, p. 37426–37434, 2026. DOI: 10.1609/aaai.v40i44.41075. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/41075. Acesso em: 31 may. 2026.