Edu-MMBias: 一种三级多模态基准，用于在教育背景下审计视觉-语言模型中的社会偏见
Edu-MMBias: A Three-Tier Multimodal Benchmark for Auditing Social Bias in Vision-Language Models under Educational Contexts
AI总结：
本文提出Edu-MMBias基准，通过三级维度审计视觉-语言模型中的社会偏见，揭示模型存在补偿性类偏见和深层健康与种族刻板印象，视觉输入可触发偏见回潮。
摘要：
随着视觉-语言模型（VLMs）在教育决策中的重要性增加，确保其公平性变得至关重要。然而，当前以文本为中心的评估忽略了视觉模态，留下了一个未受监管的潜在社会偏见通道。为此，我们提出了Edu-MMBias，一个基于社会心理学态度三成分模型的系统审计框架。该框架在三个层次维度上诊断偏见：认知、情感和行为。利用一个专门的生成管道，结合自我纠正机制和人机协同验证，我们合成出抗污染的学生档案，对最先进的VLMs进行全面压力测试。我们的广泛审计揭示了关键且反直觉的模式：模型表现出补偿性类偏见，倾向于偏好低地位叙述，同时同时存在深层次的健康和种族刻板印象。关键的是，我们发现视觉输入充当了安全回道，触发偏见的再次浮现，绕过了基于文本的对齐保障，揭示了潜在认知与最终决策之间的系统性不一致。本文的贡献详见：https://anonymous.4open.science/r/EduMMBias-63B2。
英文摘要：
As Vision-Language Models (VLMs) become integral to educational decision-making, ensuring their fairness is paramount. However, current text-centric evaluations neglect the visual modality, leaving an unregulated channel for latent social biases. To bridge this gap, we present Edu-MMBias, a systematic auditing framework grounded in the tri-component model of attitudes from social psychology. This framework diagnoses bias across three hierarchical dimensions: cognitive, affective, and behavioral. Utilizing a specialized generative pipeline that incorporates a self-correct mechanism and human-in-the-loop verification, we synthesize contamination-resistant student profiles to conduct a holistic stress test on state-of-the-art VLMs. Our extensive audit reveals critical, counter-intuitive patterns: models exhibit a compensatory class bias favoring lower-status narratives while simultaneously harboring deep-seated health and racial stereotypes. Crucially, we find that visual inputs act as a safety backdoor, triggering a resurgence of biases that bypass text-based alignment safeguards and revealing a systematic misalignment between latent cognition and final decision-making. The contributions of this paper are available at: https://anonymous.4open.science/r/EduMMBias-63B2.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
