The Male CEO and the Female Assistant: Probing Gender Biases in Text-To-Image Models Through Paired Stereotype Test

arXiv:2402.11089v1 Announce Type: new
Abstract: Recent large-scale Text-To-Image (T2I) models such as DALLE-3 demonstrate great potential in new applications, but also face unprecedented fairness challenges. Prior studies revealed gender biases in single-person image generation, but T2I model applications might require portraying two or more people simultaneously. Potential biases in this setting remain unexplored, leading to fairness-related risks in usage. To study these underlying facets of gender biases in T2I models, we propose a novel Paired Stereotype Test (PST) bias evaluation …

abstract applications arxiv assistant biases ceo challenges cs.ai cs.cv cs.cy dalle dalle-3 face fairness gender image image generation person prior scale studies test text text-to-image through type