AINeutralarXiv – CS AI · 14h ago6/10
🧠
GLEaN: A Text-to-image Bias Detection Approach for Public Comprehension
Researchers introduce GLEaN, a visual explainability method that transforms complex AI bias detection into understandable portrait composites, enabling non-technical audiences to grasp how text-to-image models like Stable Diffusion XL associate occupations and identities with specific demographic characteristics.
🧠 Stable Diffusion