AI RESEARCH
Exposing Hidden Biases in Text-to-Image Models via Automated Prompt Search
arXiv CS.LG
•
ArXi:2512.08724v2 Announce Type: replace Text-to-image (TTI) diffusion models have achieved remarkable visual quality, yet they have been repeatedly shown to exhibit social biases across sensitive attributes such as gender, race and age. To mitigate these biases, existing approaches frequently depend on curated prompt datasets - either manually constructed or generated with large language models (LLMs) - as part of their