Beyond wheelchairs and blindfolds: Investigating disability stereotypes in T2I models with INCLUDE-BENCH

• URL: http://arxiv.org/abs/2607.08515v1
• Date: Thu, 09 Jul 2026 14:10:29 GMT
• Title: Beyond wheelchairs and blindfolds: Investigating disability stereotypes in T2I models with INCLUDE-BENCH
• Abstract summary: Text-to-image (T2I) models have been shown to exhibit social biases.<n>Current evaluation practices often fail to align with sociologically grounded definitions of stereotyping.<n>We introduce -BENCH, the first largescale benchmark for evaluating disability-related bias in T2I models.
• Score: 4.4260965078852275
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-image (T2I) models have been shown to exhibit social biases. Prior work has mainly focused on gender, skin tone, and cultural representation within restricted occupational associations, and emerging benchmarks increasingly incorporate these dimensions. However, disability remains systematically underexplored. Current evaluation practices often fail to align with sociologically grounded definitions of stereotyping, limiting principled assessment of representational harms toward people with disabilities (PWD). To address this, we introduce INCLUDE-BENCH, the first large-scale benchmark for evaluating disability-related bias in T2I models. INCLUDE-BENCH comprises 119K generated images based on prompt design across multiple bias dimensions and both static and dynamic contexts. We evaluate 15 open-source and 2 closed-source models. Our key findings reveal that: (1) mobility-impaired and default disability prompts predominantly yield wheelchair depictions across all models; (2) disability-conditioned generations consistently exhibit less diversity; (3) stereotypical portrayals demonstrate stronger disability-text alignment; and (4) we introduce the Stereotype Content Model (SCM) Score, demonstrating that T2I models reflect real-world stereotypical associations.

Related papers

• Investigating Disability Representations in Text-to-Image Models [7.244686394468418]
  This study investigates how people with disabilities are represented in AI-generated images.<n>We analyze disability representations by comparing image similarities between generic disability prompts and prompts referring to specific disability categories.
  arXiv  Detail & Related papers  (2026-02-04T15:54:25Z)
• Measuring Social Bias in Vision-Language Models with Face-Only Counterfactuals from Real Photos [79.03150233804458]
  Real-world images entangle race and gender with correlated factors such as background and clothing, obscuring attribution.<n>We propose a textbfface-only counterfactual evaluation paradigm<n>We generate counterfactual variants by editing only facial attributes related to race and gender, keeping all other visual factors fixed.
  arXiv  Detail & Related papers  (2026-01-11T14:35:06Z)
• Medical Imaging AI Competitions Lack Fairness [50.895929923643905]
  We assess fairness along two complementary dimensions: whether challenge datasets are representative of real-world clinical diversity, and whether they are accessible and legally reusable in line with the FAIR principles.<n>Our findings show substantial biases in dataset composition, including geographic location, modality, and problem type-related biases, indicating that current benchmarks do not adequately reflect real-world clinical diversity.<n>These shortcomings expose foundational limitations in our benchmarking ecosystem and highlight a disconnect between leaderboard success and clinical relevance.
  arXiv  Detail & Related papers  (2025-12-19T13:48:10Z)
• AccessEval: Benchmarking Disability Bias in Large Language Models [3.160274015679566]
  Large Language Models (LLMs) are increasingly deployed across diverse domains but often exhibit disparities in how they handle real-life queries.<n>We introduce textbfAccessEval (Accessibility Evaluation), a benchmark evaluating 21 closed- and open-source LLMs across 6 real-world domains and 9 disability types.<n>Our analysis reveals that responses to disability-aware queries tend to have a more negative tone, increased stereotyping, and higher factual error compared to neutral queries.
  arXiv  Detail & Related papers  (2025-09-22T17:49:03Z)
• Who's Asking? Investigating Bias Through the Lens of Disability Framed Queries in LLMs [2.722784054643991]
  Large Language Models (LLMs) routinely infer users demographic traits from phrasing alone.<n>Disability cues in shaping these inferences remains largely uncharted.<n>We present the first systematic audit of disability-conditioned demographic bias across eight state-of-the-art instruction-tuned LLMs.
  arXiv  Detail & Related papers  (2025-08-18T21:03:09Z)
• The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models [91.86718720024825]
  We center transgender, nonbinary, and other gender-diverse identities to investigate how alignment procedures interact with pre-existing gender-diverse bias.<n>Our findings reveal that DPO-aligned models are particularly sensitive to supervised finetuning.<n>We conclude with recommendations tailored to DPO and broader alignment practices.
  arXiv  Detail & Related papers  (2024-11-06T06:50:50Z)
• Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation [47.770531682802314]
  Even simple prompts could cause T2I models to exhibit conspicuous social bias in generated images. We present the first extensive survey on bias in T2I generative models. We discuss how these works define, evaluate, and mitigate different aspects of bias.
  arXiv  Detail & Related papers  (2024-04-01T10:19:05Z)
• The Male CEO and the Female Assistant: Evaluation and Mitigation of Gender Biases in Text-To-Image Generation of Dual Subjects [58.27353205269664]
  We propose the Paired Stereotype Test (PST) framework, which queries T2I models to depict two individuals assigned with male-stereotyped and female-stereotyped social identities.<n>PST queries T2I models to depict two individuals assigned with male-stereotyped and female-stereotyped social identities.<n>Using PST, we evaluate two aspects of gender biases -- the well-known bias in gendered occupation and a novel aspect: bias in organizational power.
  arXiv  Detail & Related papers  (2024-02-16T21:32:27Z)
• Social Bias Probing: Fairness Benchmarking for Language Models [38.180696489079985]
  This paper proposes a novel framework for probing language models for social biases by assessing disparate treatment. We curate SoFa, a large-scale benchmark designed to address the limitations of existing fairness collections. We show that biases within language models are more nuanced than acknowledged, indicating a broader scope of encoded biases than previously recognized.
  arXiv  Detail & Related papers  (2023-11-15T16:35:59Z)
• Stable Bias: Analyzing Societal Representations in Diffusion Models [72.27121528451528]
  We propose a new method for exploring the social biases in Text-to-Image (TTI) systems. Our approach relies on characterizing the variation in generated images triggered by enumerating gender and ethnicity markers in the prompts. We leverage this method to analyze images generated by 3 popular TTI systems and find that while all of their outputs show correlations with US labor demographics, they also consistently under-represent marginalized identities to different extents.
  arXiv  Detail & Related papers  (2023-03-20T19:32:49Z)
• Social Biases in NLP Models as Barriers for Persons with Disabilities [13.579848462349192]
  We present evidence of undesirable biases towards mentions of disability in two different English language models: toxicity prediction and sentiment analysis. Next, we demonstrate that the neural embeddings that are the critical first step in most NLP pipelines similarly contain undesirable biases towards mentions of disability. We end by highlighting topical biases in the discourse about disability which may contribute to the observed model biases.
  arXiv  Detail & Related papers  (2020-05-02T12:16:54Z)

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.