🛰️ Daily AI Frontier
‹ back to 2026-09-11

Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems

arXiv cs.AI Multimodal & Generative Aleksandra Urman, Elsa Lichtenegger, Salima Jaoua, Azza Bouleimen, Robin Forsberg, Corinna Hertweck, Stefania Ionescu, Nicolò Pagan, Ancsa Hannak, Joachim Baumann 2026-09-10
Representative image for Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems

TL;DR - WORLDVIEW reveals that hidden prompt-revision layers in commercial text-to-image systems can causally introduce cultural stereotyping. This shows that bias audits must examine deployed generation pipelines—not just models or final images.

  • WORLDVIEW contains 8,960 prompts spanning 15 languages and 31 language-context pairings.
  • The audit covers prompt revision in DALL-E-3, Imagen-4, and GPT-Image-1.5.
  • Compared with a no-context English baseline, US contexts were least marked, while non-Western and non-Anglophone contexts received heavier cultural marking.
  • Revised prompts often compressed diverse contexts into narrow, stereotypical vocabularies; original-versus-revised prompt comparisons isolated revision as the cause.

view merged work →