Surgeons Are Indian Males and Speech Therapists Are White Females: Auditing Biases in Vision-Language Models for Healthcare Professionals
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916995896705024 |
|---|---|
| author | Siddiqui, Zohaib Hasan Nadeem, Dayam Rahman, Mohammad Masudur Nadeem, Mohammad Sohail, Shahab Saquib Chaudhry, Beenish Moalla |
| author_facet | Siddiqui, Zohaib Hasan Nadeem, Dayam Rahman, Mohammad Masudur Nadeem, Mohammad Sohail, Shahab Saquib Chaudhry, Beenish Moalla |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_06280 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Surgeons Are Indian Males and Speech Therapists Are White Females: Auditing Biases in Vision-Language Models for Healthcare Professionals Siddiqui, Zohaib Hasan Nadeem, Dayam Rahman, Mohammad Masudur Nadeem, Mohammad Sohail, Shahab Saquib Chaudhry, Beenish Moalla Computers and Society Artificial Intelligence Computer Vision and Pattern Recognition 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. |
| title | Surgeons Are Indian Males and Speech Therapists Are White Females: Auditing Biases in Vision-Language Models for Healthcare Professionals |
| topic | Computers and Society Artificial Intelligence Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2510.06280 |