3 papers
cs.CV2025
Visual Cues of Gender and Race are Associated with Stereotyping in Vision-Language Models
Messi H. J. Lee, Soyeon Jeon, Jacob M. Montgomery +1
Current research on bias in Vision Language Models (VLMs) has important limitations: it is focused exclusively on trait associations while ignoring other forms of stereotyping, it…
cs.CV2024
More Distinctively Black and Feminine Faces Lead to Increased Stereotyping in Vision-Language Models
Messi H. J. Lee, Jacob M. Montgomery, Calvin K. Lai
Vision Language Models (VLMs), exemplified by GPT-4V, adeptly integrate text and vision modalities. This integration enhances Large Language Models' ability to mimic human percepti…
cs.CL2024
Large Language Models Portray Socially Subordinate Groups as More Homogeneous, Consistent with a Bias Observed in Humans
Messi H. J. Lee, Jacob M. Montgomery, Calvin K. Lai
Large language models (LLMs) are becoming pervasive in everyday life, yet their propensity to reproduce biases inherited from training data remains a pressing concern. Prior invest…