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

• URL: http://arxiv.org/abs/2608.29847v1
• Date: Sun, 30 Aug 2026 15:23:07 GMT
• Title: ContextBias: Controlled Evaluation of Bias Persistence Under Context Shift in Text-to-Image Models
• Abstract summary: We introduce ContextBias, a controlled evaluation framework, and ContextBench, a benchmark spanning 92 roles and 1,656 semantically controlled prompts.<n>We evaluate four state-of-the-art models on 66,240 generated images.<n>We find that placing a role in a semantically unrelated context does not suppress role-linked attributes; instead, cross-role attribute concentration increases.
• Score: 56.399896249572826
• License: http://creativecommons.org/licenses/by/4.0/
• 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

Related papers

• Deeply Interleaved Text-Image Contexts for Multimodal LLMs Assessment [57.41731607488101]
  TIC-Bench is designed to evaluate the capability of models to integrate text-image clues and recover the ground truth facts within deeply interleaved contexts.<n>We evaluated 10 state-of-the-art MLLMs and observed a substantial performance gap compared to human experts.
  arXiv  Detail & Related papers  (2026-09-02T13:19:51Z)
• The Illusion of Robustness: Aggregate Accuracy Hides Prediction Flips under Task-Irrelevant Context [76.36635039699112]
  Large language models (LLMs) are increasingly deployed in context-rich settings where task inputs are often accompanied by long, partially irrelevant context.<n>We find that state-of-the-art models often appear robust to task-irrelevant context at the aggregate level.<n>This aggregate stability, however, masks significant per-example instability.
  arXiv  Detail & Related papers  (2026-07-14T17:01:12Z)
• Same Image, Different Meanings: Toward Retrieval of Context-Dependent Meanings [2.9320341537404713]
  We investigate the context-dependent nature of image meaning and its implications for retrieval.<n>Key observation is that context dependency correlates with semantic abstraction.<n>We operationalize this as the L1--L4 framework, organizing image semantics from context-independent (L1) to maximally context-dependent (L4)
  arXiv  Detail & Related papers  (2026-05-13T02:31:10Z)
• Lost in Context: The Influence of Context on Feature Attribution Methods for Object Recognition [4.674826882670651]
  This study investigates how context manipulation influences both model accuracy and feature attribution. We employ a range of feature attribution techniques to decipher the reliance of deep neural networks on context in object recognition tasks.
  arXiv  Detail & Related papers  (2024-11-05T06:13:01Z)
• Context Diffusion: In-Context Aware Image Generation [27.63447546705641]
  Context Diffusion is a diffusion-based framework that enables image generation models to learn from visual examples presented in context.<n>Our experiments and human evaluation demonstrate that Context Diffusion excels in both in-domain and out-of-domain tasks.
  arXiv  Detail & Related papers  (2023-12-06T16:19:51Z)
• Context-LGM: Leveraging Object-Context Relation for Context-Aware Object Recognition [48.5398871460388]
  We propose a novel Contextual Latent Generative Model (Context-LGM), which considers the object-context relation and models it in a hierarchical manner. To infer contextual features, we reformulate the objective function of Variational Auto-Encoder (VAE), where contextual features are learned as a posterior conditioned distribution on the object. The effectiveness of our method is verified by state-of-the-art performance on two context-aware object recognition tasks.
  arXiv  Detail & Related papers  (2021-10-08T11:31:58Z)
• Probing Contextual Language Models for Common Ground with Visual Representations [76.05769268286038]
  We design a probing model that evaluates how effective are text-only representations in distinguishing between matching and non-matching visual representations. Our findings show that language representations alone provide a strong signal for retrieving image patches from the correct object categories. Visually grounded language models slightly outperform text-only language models in instance retrieval, but greatly under-perform humans.
  arXiv  Detail & Related papers  (2020-05-01T21:28:28Z)
• Don't Judge an Object by Its Context: Learning to Overcome Contextual Bias [113.44471186752018]
  Existing models often leverage co-occurrences between objects and their context to improve recognition accuracy. This work focuses on addressing such contextual biases to improve the robustness of the learnt feature representations.
  arXiv  Detail & Related papers  (2020-01-09T18:31:55Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.