Gueorguieva, A.-M. and Caliskan, A. 2026. 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. 40, 44 (Mar. 2026), 37426–37434. DOI:https://doi.org/10.1609/aaai.v40i44.41075.