VIGNETTE: Socially Grounded Bias Evaluation for Vision-Language Models
Year: 2026
Type: conference-paper
Abstract: While bias in large language models (LLMs) is well-studied, similar concerns in vision-language models (VLMs) have received comparatively less attention. Existing VLM bias studies often focus on portrait-style images and gender-occupation associations, overlooking broader and more complex social stereotypes and their implied harm. This work introduces VIGNETTE, a large-scale VQA benchmark with 30M+ images for evaluating bias in VLMs through a question-answering framework spanning four directions: factuality, perception, stereotyping, and decision making. Beyond narrowly-centered studies, we assess how VLMs interpret identities in contextualized settings, revealing how models make trait and capability assumptions and exhibit patterns of discrimination. Drawing from social psychology, we examine how VLMs connect visual identity cues to trait and role-based inferences, encoding social hierarchies, through biased selections. Our findings uncover subtle, multifaceted, and surprising stereotypical patterns, offering insights into how VLMs construct social meaning from inputs.
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
SDG: Reduced inequalities
Open Access status: hybrid
Awards: CAREER: Leveraging Grammar Books to Develop Language Technologies for Data-Scarce Languages, III: Small: Harnessing Interpretable Neuro-Symbolic Learning for Reliable Ranking, CAREER: The Impact of Associations and Biases in Generative AI on Society, MRI: Acquisition of a Shared Scalable Research Storage System, MRI: Acquisition of an Adaptive Computing Infrastructure to Support Compute- and Data-Intensive Multidisciplinary Research, G8170989563
OpenAlex ID: W4417341952
