VIBE：通过真实世界语音对大型音频-语言模型进行语音诱导的开放式偏差评估

VIBE: Voice-Induced open-ended Bias Evaluation for Large Audio-Language Models via Real-World Speech

July 3, 2026

作者: Yi-Cheng Lin, Yusuke Hirota, Sung-Feng Huang, Hung-yi Lee

cs.AI

摘要

大型音频语言模型（LALMs）正日益融入日常应用，但其生成偏见仍鲜有深入探究。现有语音公平性基准依赖合成语音和多项选择题（MCQs），两者均只提供片段化的公平性视角。我们提出VIBE框架，通过开放任务（如个性化推荐）评估生成偏见，并采用人类录制语音。与MCQs不同，我们的方法允许刻板关联在没有预设选项的情况下自然显现，从而易于扩展至新任务。对12个最先进LALMs的评估揭示了逼真场景下的系统性偏见。性别和口音线索均引发统计上显著的分布偏移，且偏见程度高度依赖于具体任务。

English

Large Audio-Language Models (LALMs) are increasingly integrated into daily applications, yet their generative biases remain underexplored. Existing speech fairness benchmarks rely on synthetic speech and Multiple-Choice Questions (MCQs), both offering a fragmented view of fairness. We propose VIBE, a framework that evaluates generative bias through open-ended tasks such as personalized recommendations, using human-recorded speech. Unlike MCQs, our method allows stereotypical associations to manifest organically without predefined options, making it easily extensible to new tasks. Evaluating 12 state-of-the-art LALMs reveals systematic biases in realistic scenarios. Both gender and accent cues trigger statistically significant distributional shifts, and bias magnitude is strongly task-dependent.