SOURCE-LINKED INTELLIGENCE

Gender Bias in Vision-Language In-Context Learning

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

In-context learning (ICL) enables large vision-language models (LVLMs) to perform tasks by following patterns from in-context examples, yet its potential to amplify societal biases remains underexplored. We systematically investigate how ICL influences gender bias in LVLMs through VL-BICLE, an evaluation framework comprising six ICL settings, three tasks, and four datasets. Our experiments on six LVLMs reveal that gendered ICL demonstrations act as a directional force, shifting model bias toward the demonstrated gender through a cross-gender mechanism that disproportionately degrades performan

Read original source ↗ Open in workspace

recordType

paper

region

Global