Problem
Research questions and friction points this paper is trying to address.
Gender Bias
In-Context Learning
Vision-Language Models
Gender Bias in Vision-Language In-Context Learning
🤖 AI Summary
研究探讨了上下文学习对视觉-语言模型中性别偏见的影响，并提出通过使用合成图像替代真实图像来减少性别偏见的方法。
📝 Abstract
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 performance on the opposite gender. This effect appears in image captioning and pronoun prediction but not in visual question answering, indicating that gendered ICL influences bias only when the task output involves gendered language. Similarity-based retrieval methods inherit the training pool's gender imbalance and offer no debiasing advantage, while standard quality metrics remain blind to these bias shifts. To mitigate this bias, we replace real in-context images with synthetic ones from stable diffusion models while keeping captions unchanged. This simple intervention reduces gender bias without degrading caption quality.
Innovation
Methods, ideas, or system contributions that make the work stand out.
synthetic images
gender bias mitigation
in-context learning
stable diffusion models
🔎 Similar Papers
No similar papers found.
