T2I models systematically depict disability via wheelchair and blindfold tropes with reduced diversity and SCM scores that mirror real-world high-warmth/low-competence stereotypes.
Dall-eval: Probing the reasoning skills and social biases of text-to- image generation models
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
FAGER is a new agentic framework that creates structured factual rubrics to evaluate and refine text-to-image outputs for implicit factual correctness across science, history, products, and culture.
citing papers explorer
-
Beyond wheelchairs and blindfolds: Investigating disability stereotypes in T2I models with INCLUDE-BENCH
T2I models systematically depict disability via wheelchair and blindfold tropes with reduced diversity and SCM scores that mirror real-world high-warmth/low-competence stereotypes.
-
FAGER: Factually Grounded Evaluation and Refinement of Text-to-Image Models
FAGER is a new agentic framework that creates structured factual rubrics to evaluate and refine text-to-image outputs for implicit factual correctness across science, history, products, and culture.