$\texttt{ModSCAN}$: Measuring Stereotypical Bias in Large Vision-Language Models from Vision and Language Modalities
Abstract: Large vision-language models (LVLMs) have been rapidly developed and widely used in various fields, but the (potential) stereotypical bias in the model is largely unexplored.
In this study, we present a pioneering measurement framework, $\texttt{ModSCAN}$, to $\underline{\text{SCAN}}$ the stereotypical bias within LVLMs from both vision and language $\underline{\text{Mod}}$alities.
$\texttt{ModSCAN}$ examines stereotypical biases with respect to two typical stereotypical attributes (gender and race) across three kinds of scenarios: occupations, descriptors, and persona traits.
Our findings suggest that 1) the currently popular LVLMs show significant stereotype biases, with CogVLM emerging as the most biased model;
2) these stereotypical biases may stem from the inherent biases in the training dataset and pre-trained models;
3) the utilization of specific prompt prefixes (from both vision and language modalities) performs well in reducing stereotypical biases.
We believe our work can serve as the foundation for understanding and addressing stereotypical bias in LVLMs.
Paper Type: Long
Research Area: Ethics, Bias, and Fairness
Research Area Keywords: model bias/fairness evaluation; model bias/unfairness mitigation
Contribution Types: Model analysis & interpretability, Data analysis
Languages Studied: English
Submission Number: 3349
Loading