Existing works examining Vision Language Models (VLMs) for social biases
predominantly focus on a limited set of documented bias associations, such as
gender:profession or race:crime. This narrow scope often overlooks a vast range
of unexamined implicit associations, restricting the identification and, hence,
mitigation of such biases. We address this gap by probing VLMs to (1) uncover
hidden, implicit associations across 9 bias dimensions. We systematically
explore diverse input and output modalities and (2) demonstrate how biased
associations vary in their negativity, toxicity, and extremity. Our work (3)
identifies subtle and extreme biases that are typically not recognized by
existing methodologies. We make the Dataset of retrieved associations, (Dora),
publicly available here this https URL

通过检测视觉语言模型（VLMs）上的隐藏、隐含性关联，系统地探索多元的输入和输出模式，揭示存在于九个偏见维度上的细微和极端偏见，从而填补了现有方法的不足，发现通常不被现有方法识别到的隐秘和极端偏见，同时公开了关联数据集（Dora）。