Peer reviewed publications

Gueorguieva, A-M., Caliskan, A., Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Mitigation with Guardrail Models, Proceedings of the AAAI Conference on Artificial Intelligence, AI Alignment Track 2026

Wilson, K., Sim, M., Gueorguieva, A-M., Caliskan, A., No Thoughts Just AI: Biased Hiring Recommendations Alter Human Decision Making and Limit Human Autonomy, Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society (AIES) 2025; reported on by the Washington Post

Sun, Y., Gueorguieva, A-M., Caliskan, A., VEAT Quantifies Implicit Associations in Text-to-Video Generator Sora and Reveals Challenges in Bias Mitigation, Proceedings of 2nd Annual Conference International Association for Safe & Ethical AI (IASEAI) 2026

Guldimann, P., Spiridonov, A., Staab, R., Jovanović, N., Vechev, V., Gueorguieva, A-M., Balunović, M., Konstantinov, N., Bielik, P., Tsankov, P., Vechev, M. COMPL-AI Framework: A Technical Interpretation and LLM Benchmarking Suite for the EU Artificial Intelligence Act October 2024. Interactive website for evaluating LLM models based on the work linked here

Other writing and policy contributions

Gueorguieva, A-M., Cruz, S., Kallina, E., Kraft-Buchman C., Human Rights, Transparency, and Stakeholder Involvement in AI Accountability: Public Comment Submitted to the United States National Telecommunications and Information Administration <AI & Equality>, June 2023. (Cited by NTIA’s AI Accountability Report)

Gueorguieva, A-M., The Effectiveness and Future of United States Executive Orders to Promote Human-Rights Based Artificial Intelligence Re-visions of Now & Future: Commentary & Research on Contemporary AI and a Way Forward, Vol. 2, Chapter 2, <AI & Equality>, October 2024