Preprint
Sep 2026
IMPLICIT-Bench: Measuring Implicit Bias in Text-to-Image Models under Neutral Prompts
Text-to-image (T2I) models are typically evaluated for bias using slot-based templates such as ``a photo of a [profession]''. Such templates probe only \emph{explicit} demographic attributes (e.g., gender, skin tone) in isolation. They overlook a broader \emph{implicit} bias that arises in natural prompts: when stereot...
Yue Dai, Zi-Yang Liu, Marc Cheong et al.
· 0 citations