Gueorguieva A-M, Caliskan A. Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 31];40(44):37426-34. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/41075