Researchers at the Technical University of Munich (TUM) and TU Darmstadt have studied how text-to-image generators deal with gender stereotypes in various languages. The results show that the models not only reflect gender biases, but also amplify them. The direction and strength of the distortion depends on the language in question.
Strength of gender biases in AI images varies across languages
Reader’s Picks
-
In July 2025, a letter from an English city council neighborhood services officer circulated on social media.This article is brought [...]
-
A visitor to Japan who wanders into a sumo tournament might be forgiven for thinking they had intruded upon a [...]
-
Approximately 10% of adult women and 5% of adult men report being a victim of spiking, and almost half of [...]