mlsanityData to 13 Oct 2026

Surgeons Are Indian Males and Speech Therapists Are White Females: Auditing Biases in Vision-Language Models for Healthcare Professionals

arXiv 2510.06280 ↗First posted 6 Oct 2025cs.CY cs.AI cs.CVcited by 1

On the map: Multimodal LLMs / vision-language models → Medical vision-language models

Abstract (arXiv)

Vision language models (VLMs), such as CLIP and OpenCLIP, can encode and reflect stereotypical associations between medical professions and demographic attributes learned from web-scale data. We present an evaluation protocol for healthcare settings that quantifies associated biases and assesses their operational risk. Our methodology (i) defines a taxonomy spanning clinicians and allied healthcare roles (e.g., surgeon, cardiologist, dentist, nurse, pharmacist, technician), (ii) curates a profession-aware prompt suite to probe model behavior, and (iii) benchmarks demographic skew against a balanced face corpus. Empirically, we observe consistent demographic biases across multiple roles and vision models. Our work highlights the importance of bias identification in critical domains such as healthcare as AI-enabled hiring and workforce analytics can have downstream implications for equity, compliance, and patient trust.

Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Placed in Medical vision-language models, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 23 of its 32 references that are in the map. First posted on arXiv 6 Oct 2025.

Builds on

23 of 32 references.

References · 23

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,588
  2. 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,141
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,686
  4. 2022Reproducible scaling laws for contrastive language-image learningcited by 1,164
  5. 2017Age Progression/Regression by Conditional Adversarial Autoencodercited by 428
  6. 2024FairCLIP: Harnessing Fairness in Vision-Language Learningcited by 69
  7. 2022MEDFAIR: Benchmarking Fairness for Medical Imagingcited by 66
  8. 2025Vision Language Models are Biasedcited by 64
  9. 2023SocialCounterfactuals: Probing and Mitigating Intersectional Social Biases in Vision-Language Models with Counterfactual Examplescited by 53
  10. 2020Multimodal Generative Learning Utilizing Jensen-Shannon-Divergencecited by 48
  11. 2024FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Modelscited by 47
  12. 2023CLIP in Medical Imaging: A Surveycited by 40
11 more
  1. 2024Identifying Implicit Social Biases in Vision-Language Modelscited by 27
  2. 2023MultiModal Bias: Introducing a Framework for Stereotypical Bias Assessment beyond Gender and Race in Vision Language Modelscited by 23
  3. 2024Joint Vision-Language Social Bias Removal for CLIPcited by 18
  4. 2024BiasDora: Exploring Hidden Biased Associations in Vision-Language Modelscited by 12
  5. 2024A Unified Framework and Dataset for Assessing Societal Bias in Vision-Language Modelscited by 11
  6. 2024Gender Bias in Text-to-Video Generation Models: A case study of Soracited by 8
  7. 2024The Bias of Harmful Label Associations in Vision-Language Modelscited by 5
  8. 2025Vision-Language Models display a strong gender biascited by 5
  9. 2025Freeze and Reveal: Exposing Modality Bias in Vision-Language Modelscited by 2
  10. 2025Owls are wise and foxes are unfaithful: Uncovering animal stereotypes in vision-language modelscited by 1
  11. 2025Visual Cues of Gender and Race are Associated with Stereotyping in Vision-Language Modelscited by 1

Built on by

Cited by year (2026 to 13 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026IndicFairFace: Balanced Indian Face Dataset for Auditing and Mitigating Geographical Bias in Vision-Language Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Demographic Bias of Expert-Level Vision-Language Foundation Models in Medical Imaging
  2. 2026FairLens: Benchmarking Fairness in Vision-Language Models for High-Stakes Decision-Making
  3. 2025Elucidating Mechanisms of Demographic Bias in LLMs for Healthcare
  4. 2024Bias patterns in the application of LLMs for clinical decision support: A comprehensive study
  5. 2024CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
  6. 2025DemoBias: An Empirical Study to Trace Demographic Biases in Vision Foundation Models
  7. 2025BiasICL: In-Context Learning and Demographic Biases of Vision Language Models
  8. 2024FMBench: Benchmarking Fairness in Multimodal Large Language Models on Medical Tasks