ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models

2026-08-30

AI Summary

研究通过ContextBias框架评估文本到图像模型在不同语境下职业角色偏见的稳定性，发现即使改变语境，与角色相关的视觉属性仍保持不变。

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

Problem

• Text-to-Image Models
• Context Shift
• Role-linked Attributes
• Stereotypical Bias
• Visual Representations

Innovation

• ContextBias
• Contextual Variation
• Stereotypical Persistence
• Text-to-Image Models