Gueorguieva, A.-M., & 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), 37426–37434. https://doi.org/10.1609/aaai.v40i44.41075