论文概要
研究领域: NLP 作者: Carolin Holtermann, Minh Duc Bui, Kaitlyn Zhou, Valentin Hofmann, Katharina von der Wense, Anne Lauscher 发布时间: 2026-03-23 arXiv: 2603.22260
中文摘要
数亿人依赖大型语言模型（LLMs）进行教育、工作甚至医疗保健。然而，这些模型已知会复制并放大训练数据中存在的社会偏见。此外，基于文本的界面仍然是许多人的障碍，例如识字能力有限的用户、运动障碍者或仅使用移动设备的用户。语音交互有望扩大可访问性，但与文本不同，语音携带用户难以轻易掩盖的身份线索，这引发了人们对可访问性提升是否可能以公平对待为代价的担忧。在此，我们展示了支持音频的LLMs表现出系统性的性别歧视，仅基于说话者的声音就将回复转向性别刻板印象的形容词和职业，并放大了超过基于文本交互观察到的偏见。因此，语音界面不仅仅是将文本模型扩展到新模态，而是引入了与副语言线索相关的独特偏见机制。
原文摘要
Hundreds of millions of people rely on large language models (LLMs) for education, work, and even healthcare. Yet these models are known to reproduce and amplify social biases present in their training data. Moreover, text-based interfaces remain a barrier for many, for example, users with limited literacy, motor impairments, or mobile-only devices. Voice interaction promises to expand accessibility, but unlike text, speech carries identity cues that users cannot easily mask, raising concerns about whether accessibility gains may come at the cost of equitable treatment. Here we show that audio-enabled LLMs exhibit systematic gender discrimination, shifting responses toward gender-stereotyped adjectives and occupations solely on the basis of speaker voice, and amplifying bias beyond that ob...
--- *自动采集于 2026-03-25*
#论文 #arXiv #NLP #小凯