AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

How Bias Binds: Measuring Hidden Associations for Bias Control in Text-to-Image Compositions

Jeng-Lin Li, Ming-Ching Chang, Wei-Chao Chen

AAAI 2026 · Image generation › Text-to-image diffusion · approach: Fairness and bias in generative models · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add BA-Score initialization (ablation)CBC · Winobias compositional promptsAFS: 0.68 -> 0.75Improved
use BA-Score instead of semantic-similarity initialization (ablation)CBC · Winobias compositional promptsAFS: 0.64 -> 0.75Improved
set delta_c to 2 rather than 1 (ablation)CBC · Winobias compositional promptsAFS: 0.73 -> 0.75Improved
set delta_c to 2 rather than 5 (ablation)CBC · Winobias compositional promptsAFS: 0.71 -> 0.75Improved
set delta_r to 0.2 rather than 0.5 (ablation)CBC · Winobias compositional promptsFD: 0.12 -> 0.04Improved
set delta_r to 0.2 rather than 0.3 (ablation)CBC · Winobias compositional promptsAFS: 0.74 -> 0.75No clear effect
use CBC instead of FairQueueSD-1.5 · Winobias compositional promptsAFS: 0.60 -> 0.75Improved
use CBC instead of SD-1.5SD-1.5 · Winobias compositional promptsFD: 0.69 -> 0.04Improved
use SelfDisc debiasingSD-1.5 · Winobias compositional promptsFD: 0.69 -> 0.61No clear effect
use DGDebias debiasingSD-1.5 · Winobias compositional promptsAFS: 0.41 -> 0.35Hurt
use FairQueue debiasingSD-1.5 · Winobias compositional promptsVQA: 0.63 -> 0.45Hurt
add CBC on plain (non-compositional) promptsSD-1.5 · Winobias plain promptsAFS: 0.44 -> 0.80Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy