AIBearisharXiv – CS AI · 7h ago7/10
🧠
Vision-Language Models Suppress Female Representations Under Ambiguous Input
Researchers discovered that vision-language models suppress female representations in their outputs when processing ambiguous images, despite internally encoding female associations. The study introduces LALS, a new metric revealing that models systematically filter out female signals before generation while amplifying male signals, indicating a critical gap between internal model knowledge and biased outputs.