Investigating Disability Representations in Text-to-Image Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918360662409216 |
|---|---|
| author | Tian, Yang Fan, Yu Zavolokina, Liudmila Ebling, Sarah |
| author_facet | Tian, Yang Fan, Yu Zavolokina, Liudmila Ebling, Sarah |
| contents | Text-to-image generative models have made remarkable progress in producing high-quality visual content from textual descriptions, yet concerns remain about how they represent social groups. While characteristics like gender and race have received increasing attention, disability representations remain underexplored. This study investigates how people with disabilities are represented in AI-generated images by analyzing outputs from Stable Diffusion XL and DALL-E 3 using a structured prompt design. We analyze disability representations by comparing image similarities between generic disability prompts and prompts referring to specific disability categories. Moreover, we evaluate how mitigation strategies influence disability portrayals, with a focus on assessing affective framing through sentiment polarity analysis, combining both automatic and human evaluation. Our findings reveal persistent representational imbalances and highlight the need for continuous evaluation and refinement of generative models to foster more diverse and inclusive portrayals of disability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_04687 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Investigating Disability Representations in Text-to-Image Models Tian, Yang Fan, Yu Zavolokina, Liudmila Ebling, Sarah Computation and Language Computer Vision and Pattern Recognition Computers and Society Human-Computer Interaction Text-to-image generative models have made remarkable progress in producing high-quality visual content from textual descriptions, yet concerns remain about how they represent social groups. While characteristics like gender and race have received increasing attention, disability representations remain underexplored. This study investigates how people with disabilities are represented in AI-generated images by analyzing outputs from Stable Diffusion XL and DALL-E 3 using a structured prompt design. We analyze disability representations by comparing image similarities between generic disability prompts and prompts referring to specific disability categories. Moreover, we evaluate how mitigation strategies influence disability portrayals, with a focus on assessing affective framing through sentiment polarity analysis, combining both automatic and human evaluation. Our findings reveal persistent representational imbalances and highlight the need for continuous evaluation and refinement of generative models to foster more diverse and inclusive portrayals of disability. |
| title | Investigating Disability Representations in Text-to-Image Models |
| topic | Computation and Language Computer Vision and Pattern Recognition Computers and Society Human-Computer Interaction |
| url | https://arxiv.org/abs/2602.04687 |