发表机构
Amirkabir University of Technology; King’s College London; University of Tehran; Bocconi University（阿米尔卡比尔理工大学; 伦敦国王学院; 德黑兰大学; 博科尼大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究推出多模态数据集Symphony-Bias，评估多模态模型在乐器性别关联上的偏见，发现多数结果符合社会研究，契合度随文本、视觉、音频依次减弱。
AI 中文摘要
大语言模型（LLMs）正日益融入日常生活，被广泛用于信息查询，引发了人们对其可能延续社会偏见、强化刻板印象的担忧。本研究从乐器关联的视角探究LLMs中的性别偏见，基于乐器文化性别定型的社会科学研究，推出涵盖文本、视觉、音频的平行多模态数据集Symphony-Bias。我们评估了10种不同架构和规模的多模态模型，针对22种乐器，分析它们在文本、视觉、音频三种模态下，将每种乐器与男性、女性、非二元三种性别类别的关联情况。结果显示，92%的乐器层面结果与先前社会科学研究发现一致，竖琴和鼓在所有评估模型及模态中展现出尤为一致的性别关联；我们还发现，音频与社会刻板印象的契合度最弱，视觉更强，文本最强，表明特定模态表征会以不同方式放大乐器的性别关联。注：Symphony-Bias数据集将在论文录用后公开。
英文摘要
Large language models (LLMs) are increasingly embedded in everyday life and widely used for information seeking, raising concerns about their potential to perpetuate social biases and reinforce stereotypes. In this study, we investigate gender bias in LLMs through the lens of their associations with musical instruments. Building on social-science research on the cultural gender-typing of instruments, we introduce Symphony-Bias, a parallel multimodal dataset spanning text, vision, and audio. We evaluate ten multimodal models with diverse architectures and scales across 22 musical instruments, analyzing how they associate each instrument with three gender categories: {male, female, non-binary}, across three modalities: {text, vision, audio}. Our results show that 92\% of instrument-level outcomes align with prior social-science findings, with the harp and drums showing particularly consistent gendered associations across all evaluated models and modalities. We further find that alignment with social stereotypes is weakest in audio, stronger in vision, and strongest in text, suggesting that modality-specific representations can differentially amplify gendered associations with musical instruments.\footnote{The Symphony-Bias dataset will be publicly released upon acceptance of the paper.}
Comments32 pages, 23 figures, 21 tables
