How Reasoning Influences Intersectional Biases in Vision Language Models

• URL: http://arxiv.org/abs/2511.06005v1
• Date: Sat, 08 Nov 2025 13:25:04 GMT
• Title: How Reasoning Influences Intersectional Biases in Vision Language Models
• Authors: Adit Desai, Sudipta Roy, Mohna Chakraborty,
• Abstract summary: Vision Language Models (VLMs) are increasingly deployed across downstream tasks.<n>Their training data often encode social biases that surface in outputs.<n>By analyzing how a VLM reasons, we can understand how inherent biases are perpetuated and can adversely affect downstream performance.
• Score: 5.894342004453925
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Vision Language Models (VLMs) are increasingly deployed across downstream tasks, yet their training data often encode social biases that surface in outputs. Unlike humans, who interpret images through contextual and social cues, VLMs process them through statistical associations, often leading to reasoning that diverges from human reasoning. By analyzing how a VLM reasons, we can understand how inherent biases are perpetuated and can adversely affect downstream performance. To examine this gap, we systematically analyze social biases in five open-source VLMs for an occupation prediction task, on the FairFace dataset. Across 32 occupations and three different prompting styles, we elicit both predictions and reasoning. Our findings reveal that the biased reasoning patterns systematically underlie intersectional disparities, highlighting the need to align VLM reasoning with human values prior to its downstream deployment.

Related papers

• Interpretable Debiasing of Vision-Language Models for Social Fairness [55.85977929985967]
  We introduce an interpretable, model-agnostic bias mitigation framework, DeBiasLens, that localizes social attribute neurons in Vision-Language models.<n>We train SAEs on facial image or caption datasets without corresponding social attribute labels to uncover neurons highly responsive to specific demographics.<n>Our research lays the groundwork for future auditing tools, prioritizing social fairness in emerging real-world AI systems.
  arXiv  Detail & Related papers  (2026-02-27T13:37:11Z)
• Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning [79.95774256444956]
  The lack of reasoning capabilities in Vision-Language Models has remained at the forefront of research discourse.<n>We investigate the data underlying the popular VLMs OpenCLIP, LLaVA-1.5 and Molmo through the lens of theories from pragmatics.
  arXiv  Detail & Related papers  (2026-02-26T18:54:06Z)
• 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)
• Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment [49.81946749379338]
  This work seeks to analyze the capacity of Transformers-based systems to learn demographic biases present in the data.<n>We propose a privacy-enhancing framework to reduce gender information from the learning pipeline as a way to mitigate biased behaviors in the final tools.
  arXiv  Detail & Related papers  (2025-06-13T15:29:43Z)
• VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models [23.329280888159744]
  This work introduces VIGNETTE, a large-scale VQA benchmark with 30M+ images for evaluating bias in vision-language models (VLMs)<n>We assess how VLMs interpret identities in contextualized settings, revealing how models make trait and capability assumptions and exhibit patterns of discrimination.<n>Our findings uncover subtle, multifaceted, and surprising stereotypical patterns, offering insights into how VLMs construct social meaning from inputs.
  arXiv  Detail & Related papers  (2025-05-28T22:00:30Z)
• Interpreting Social Bias in LVLMs via Information Flow Analysis and Multi-Round Dialogue Evaluation [1.7997395646080083]
  Large Vision Language Models (LVLMs) have achieved remarkable progress in multimodal tasks, yet they also exhibit notable social biases.<n>We propose an explanatory framework that combines information flow analysis with multi-round dialogue evaluation.<n>Experiments reveal that LVLMs exhibit systematic disparities in information usage when processing images of different demographic groups.
  arXiv  Detail & Related papers  (2025-05-27T12:28:44Z)
• My Answer Is NOT 'Fair': Mitigating Social Bias in Vision-Language Models via Fair and Biased Residuals [6.321884145362591]
  We focus on evaluating and mitigating social bias on both the model's response and probability distribution.<n>We find that models suffer from generating gender-biased or race-biased responses.<n>We propose a post-hoc method for the inference stage to mitigate social bias, which is training-free and model-agnostic.
  arXiv  Detail & Related papers  (2025-05-26T15:14:16Z)
• VisuLogic: A Benchmark for Evaluating Visual Reasoning in Multi-modal Large Language Models [121.03333569013148]
  We introduce VisuLogic: a benchmark of 1,000 human-verified problems across six categories.<n>These types of questions can be evaluated to assess the visual reasoning capabilities of MLLMs from multiple perspectives.<n>Most models score below 30% accuracy-only slightly above the 25% random baseline and far below the 51.4% achieved by humans.
  arXiv  Detail & Related papers  (2025-04-21T17:59:53Z)
• Actions Speak Louder than Words: Agent Decisions Reveal Implicit Biases in Language Models [10.565316815513235]
  Large language models (LLMs) may still exhibit implicit biases when simulating human behavior.<n>We show that state-of-the-art LLMs exhibit significant sociodemographic disparities in nearly all simulations.<n>When comparing our findings to real-world disparities reported in empirical studies, we find that the biases we uncovered are directionally aligned but markedly amplified.
  arXiv  Detail & Related papers  (2025-01-29T05:21:31Z)
• A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Models [9.025958469582363]
  We propose a unified framework for evaluating gender, race, and age biases in vision-language models (VLMs) We generate high-quality synthetic datasets that intentionally conceal gender, race, and age information across different professional domains. The dataset includes action-based descriptions of each profession and serves as a benchmark for evaluating societal biases in vision-language models (VLMs)
  arXiv  Detail & Related papers  (2024-02-21T09:17:51Z)
• Exploring the Jungle of Bias: Political Bias Attribution in Language Models via Dependency Analysis [86.49858739347412]
  Large Language Models (LLMs) have sparked intense debate regarding the prevalence of bias in these models and its mitigation. We propose a prompt-based method for the extraction of confounding and mediating attributes which contribute to the decision process. We find that the observed disparate treatment can at least in part be attributed to confounding and mitigating attributes and model misalignment.
  arXiv  Detail & Related papers  (2023-11-15T00:02:25Z)
• Bias and Fairness in Large Language Models: A Survey [73.87651986156006]
  We present a comprehensive survey of bias evaluation and mitigation techniques for large language models (LLMs) We first consolidate, formalize, and expand notions of social bias and fairness in natural language processing. We then unify the literature by proposing three intuitive, two for bias evaluation, and one for mitigation.
  arXiv  Detail & Related papers  (2023-09-02T00:32:55Z)

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.