AAAI 2026technical0 citations
How Bias Binds: Measuring Hidden Associations for Bias Control in Text-to-Image Compositions
Jeng-Lin Li, Ming-Ching Chang, Wei-Chao Chen
Abstract
Text-to-image generative models often exhibit bias related to sensitive attributes. However, current research tends to focus narrowly on single-object prompts with limited contextual diversity. In reality, each object or attribute within a prompt can contribute to bias. For example, the prompt ``an assistant wearing a pink hat
BibTeX
@inproceedings{aaai2026_howbiasbindsmeas,
title = {How Bias Binds: Measuring Hidden Associations for Bias Control in Text-to-Image Compositions},
author = {Jeng-Lin Li and Ming-Ching Chang and Wei-Chao Chen},
booktitle = {AAAI 2026},
year = {2026}
}