ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models
Summary
This paper introduces ContextBias and ContextBench to evaluate bias persistence in text-to-image models, finding that bias increases in semantically unrelated contexts.
View Cached Full Text
Cached at: 09/01/26, 03:40 PM
Paper page - ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models
Source: https://huggingface.co/papers/2608.29847 Published on Aug 30
·
Submitted byhttps://huggingface.co/shaghayegh
kollion Sep 1
Abstract
Text-to-image models exhibit persistent role-linked visual stereotypes across varied contexts, with cross-role attribute concentration increasing rather than diminishing under unrelated prompts.
Text-to-image modelslearn 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 ofstereotypical 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 introduceContextBias, a controlled evaluation framework, andContextBench, 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 concentrationincreases (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 compositionandcamera framingshow 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
View arXiv pageView PDFAdd to collection
Get this paper in your agent:
hf papers read 2608\.29847
Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash
Models citing this paper0
No model linking this paper
Cite arxiv.org/abs/2608.29847 in a model README.md to link it from this page.
Datasets citing this paper0
No dataset linking this paper
Cite arxiv.org/abs/2608.29847 in a dataset README.md to link it from this page.
Spaces citing this paper0
No Space linking this paper
Cite arxiv.org/abs/2608.29847 in a Space README.md to link it from this page.
Collections including this paper0
No Collection including this paper
Add this paper to acollectionto link it from this page.
Similar Articles
The Cost of Context: Mitigating Textual Bias in Multimodal Retrieval-Augmented Generation
This paper identifies and formalizes 'recorruption' in multimodal RAG, where adding accurate context causes models to abandon correct predictions due to attentional collapse (visual blindness and positional bias). The authors propose BAIR, a parameter-free inference-time framework that restores visual saliency and penalizes textual distractors, improving reliability across medical, fairness, and geospatial benchmarks.
When Irrelevant Text Matters: Affine Margin Shifts in Multimodal Large Language Models
This paper studies how irrelevant text context biases predictions in multimodal large language models, showing that context-induced decision margins follow an affine transformation of context-free margins, offering insights into model sensitivity.
HierBias: Context-Conditioned Hierarchical Media Bias Detection with Multi-Task Type Classification
HierBias introduces a hierarchical context-conditioned model for media bias detection that leverages document context to improve sentence-level classification, achieving state-of-the-art F1 and MCC on the BABE and BASIL datasets.
Efficient bias mitigation in T2I diffusion models using Concept Graphs
The paper introduces CO-ALIGN, a bias mitigation method for text-to-image diffusion models that aligns concept graphs in the text encoder and denoiser, achieving 30% fairness improvement and 11.4 FID gain while reducing incoherent outputs by 88%.
OptimismBench: Forecasting Bias and the Alignment Effect in Language Model Judgment
This paper introduces OptimismBench, a benchmark that uses inverted pairs to detect directional bias in language model probability judgments. It finds that most models exhibit optimism bias, and that alignment (post-training) amplifies this tilt, with model identity dominating language effects.