3 papers
cs.CY2026
VEAT Quantifies Implicit Associations in Text-to-Video Generator Sora and Reveals Challenges in Bias Mitigation
Yongxu Sun, Michael Saxon, Ian Yang +2
Text-to-Video (T2V) generators such as Sora raise concerns about whether generated content reflects societal bias. We extend embedding-association tests from words and images to vi…
cs.CL2025
Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation
Anna-Maria Gueorguieva, Aylin Caliskan
Large language models (LLMs) have been shown to exhibit social bias, however, bias towards non-protected stigmatized identities remain understudied. Furthermore, what social featur…
cs.CY2025
No Thoughts Just AI: Biased LLM Hiring Recommendations Alter Human Decision Making and Limit Human Autonomy
Kyra Wilson, Mattea Sim, Anna-Maria Gueorguieva +1
In this study, we conduct a resume-screening experiment (N=528) where people collaborate with simulated AI models exhibiting race-based preferences (bias) to evaluate candidates fo…