VEAT Quantifies Implicit Associations in Text-to-Video Generator Sora and Reveals Challenges in Bias Mitigation
Identifying Features Associated with Bias Against 93 Stigmatized Groups in Language Models and Guardrail Model Safety Mitigation
Ethics in Computer Security Research: A Data-Driven Assessment of the Past, the Present, and the Possible Future
What Are Chatbots’ Stereotypes About? A Data-Driven Analysis of Large Language Models’ Content Associations with Social Categories
Biased AI Outputs Can Impact Humans’ Implicit Bias: A Case Study of the Impact of Gender-Biased Text-to-Image Generators
No Thoughts Just AI: Biased LLM Hiring Recommendations Alter Human Decision Making and Limit Human Autonomy
Bias Amplification in Stable Diffusion’s Representation of Stigma Through Skin Tones and Their Homogeneity