ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models
cs.CV, cs.CL
Submitted: 2026-08-30
Updated: 2026-08-30
Comments: Accepted to EMNLP 2026
Code: https://github.com/Sina-Emami/ContextBias
License: http://creativecommons.org/licenses/by/4.0/
The gist: Text-to-image models learn associations between concepts - in the case of this paper, people's professions, which we refer to as roles - and visual attributes.
Terminology
Abstract
Text-to-image models learn associations between concepts - in the case of this paper, people's professions, which we refer to as roles - and visual attributes. These associations can underpin many observed forms of stereotypical bias. A key open question in this area is whether these associations are stable or change when visual representations of people in professional roles are placed in different prompted contexts. We introduce ContextBias, a controlled evaluation framework, and ContextBench, a benchmark spanning 92 roles and 1,656 semantically controlled prompts, designed to isolate the effect of contextual variation on role-linked visual representations. Evaluating four state-of-the-art models on 66,240 generated images, we find that placing a role in a semantically unrelated context does not suppress role-linked attributes; instead, cross-role attribute concentration increases (pooled BI +0.047). Demographic cues, characteristic garments, and role-specific tools remain highly prevalent across context-free, related, and unrelated conditions, and are robust to semantic prompt reformulation. Scene composition and camera framing show the greatest context-sensitivity. These findings reveal a form of stereotypical persistence that remains largely invisible to context-free evaluations, highlighting the need for controlled contextual variation in bias benchmarking. Code and dataset: https://huggingface.co/datasets/shaghayegh/ContextBias, https://github.com/Sina-Emami/ContextBias
Sources
- Can we Debias Social Stereotypes in AI-Generated Images? Examining Text-to-Image Outputs and User Perceptions
- FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space
- A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models
- StylisticBias: A Few Human Visual Cues Drive Most Social Biases in MLLMs
- Improving Text-to-Image Consistency via Automatic Prompt Optimization
- Investigating Social Bias in Narrative Image Generation
- Aligned but Stereotypical? How System Prompts Shape Demographic Bias in LLM-Based Text-to-Image Models
- Prompting Away Stereotypes? Evaluating Bias in Text-to-Image Models for Occupations
- OpenAI GPT-5 System Card
- Qwen-Image Technical Report
- MIST: Mitigating Intersectional Bias with Disentangled Cross-Attention Editing in Text-to-Image Diffusion Models
- Neuron-Level Interventions for Gendered and Gender-Neutral Generation in Language Models
- Improving Compositional Attribute Binding in Text-to-Image Generative Models via Enhanced Text Embeddings
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models