What type of study is this?

This is a Quantitative Study study.

October 5, 2025Open Access

Beyond the Prompt: Gender Bias in Text-to-Image Models, with a Case Study on Hospital Professions

View Full Paper

Ask AI

Bookmark

Systematic gender bias was found in text-to-image models generating images for hospital professions.
All models produced nurses as women and surgeons predominantly as men, revealing occupational stereotypes.
Prompt wording significantly impacted gender representations, altering outcomes across different models.
The need for bias-aware design and balanced defaults in generative AI is critical to prevent stereotype reinforcement.

No takes yet. Share an insight, caveat, or question.

This analysis uncovers gender bias in TTI models related to hospital professions, suggesting prompt influences outcome.

Vandewiele et al. (2025) studied this question.

View Full Paper

Ask AI

Bookmark