5 papers
Implicit Bias-Like Patterns in Reasoning Models
Messi H. J. Lee, Calvin K. Lai
Implicit biases refer to automatic mental processes that shape perceptions, judgments, and behaviors. Previous research on "implicit bias" in LLMs focused primarily on outputs rath…
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…
Probability of Differentiation Reveals Brittleness of Homogeneity Bias in GPT-4
Messi H. J. Lee, Calvin K. Lai
Homogeneity bias in Large Language Models (LLMs) refers to their tendency to homogenize the representations of some groups compared to others. Previous studies documenting this bia…
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…
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…