AIBearisharXiv – CS AI · Apr 147/10
🧠
Demographic and Linguistic Bias Evaluation in Omnimodal Language Models
Researchers evaluated four omnimodal AI models across text, image, audio, and video processing, finding substantial demographic and linguistic biases particularly in audio understanding tasks. The study reveals significant accuracy disparities across age, gender, language, and skin tone, with audio tasks showing prediction collapse toward narrow categories, highlighting fairness concerns as these models see wider real-world deployment.