Standard gender-bias detectors for text-to-image models deviate substantially from human-annotated bias, and a face-filtering plus CLIP pipeline measures bias more accurately.
A Friendly Face: Do Text-to-Image Systems Rely on Stereotypes when the Input is Under-Specified?
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
As text-to-image systems continue to grow in popularity with the general public, questions have arisen about bias and diversity in the generated images. Here, we investigate properties of images generated in response to prompts which are visually under-specified, but contain salient social attributes (e.g., 'a portrait of a threatening person' versus 'a portrait of a friendly person'). Grounding our work in social cognition theory, we find that in many cases, images contain similar demographic biases to those reported in the stereotype literature. However, trends are inconsistent across different models and further investigation is warranted.
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?
Standard gender-bias detectors for text-to-image models deviate substantially from human-annotated bias, and a face-filtering plus CLIP pipeline measures bias more accurately.