生成模态工人：跨模型审计41个职业中LLM生成人设的种族与性别
Generating the Modal Worker: A Cross-Model Audit of Race and Gender in LLM-Generated Personas Across 41 Occupations
AI总结：
本研究审计了四个大型语言模型生成的150多万个职业人设，通过与BLS数据对比，发现模型压缩了人口统计变异，系统性地扭曲了种族和性别代表性。
摘要：
随着生成式AI工具越来越多地被用于描绘职业角色中的人物，理解其种族和性别代表性偏差至关重要。我们审计了由四个主要大型语言模型（GPT-4、Gemini 2.5、DeepSeek V3.1和Mistral-medium）生成的41个美国职业中的150多万个职业人设。将这些人与美国劳工统计局（BLS）数据进行比较，我们发现模型生成的人口统计数据比真实世界数据的变异性更小，实际上将每个职业压缩为一种主导人口统计特征，而不是代表总体水平的变异。通过偏移/夸张分解揭示了这些扭曲的结构：白人（-31个百分点）和黑人（-9个百分点）工人持续被低估，而西班牙裔（+17个百分点）和亚裔（+12个百分点）工人被高估，刻板印象的夸张加剧了现有的职业隔离。这些扭曲往往极端，包括几乎全部将管家描绘为西班牙裔，以及许多职业中黑人工人几乎被抹去。由于这些模式在不同机构和文化起源的模型中重复出现，它们表明存在共享的结构性偏差来源，而非模型特定的伪影。我们认为，审计生成式AI需要评估框架，该框架检查合成人口如何系统地重塑跨社会角色的人口统计可见性。
英文摘要：
As generative AI tools are increasingly used to portray people in professional roles, understanding their racial and gender representational biases is critical. We audit over 1.5 million occupational personas generated by four major large language models (GPT-4, Gemini 2.5, DeepSeek V3.1, and Mistral-medium) across 41 U.S. occupations. Comparing these personas against U.S. Bureau of Labor Statistics (BLS) data, we find that models generate demographics with less variation than real-world data, functionally compressing each occupation toward a dominant demographic profile rather than representing population-level variation. A shift/exaggeration decomposition reveals the structure of these distortions: White (-31 percentage points) and Black (-9 pp) workers are consistently underrepresented, while Hispanic (+17 pp) and Asian (+12 pp) workers are overrepresented, with stereotype exaggeration amplifying existing occupational segregation. These distortions are often extreme, including near-total portrayals of housekeepers as Hispanic and the near-erasure of Black workers from many occupations. Because these patterns recur across models with different institutional and cultural origins, they suggest shared structural sources of bias rather than model-specific artifacts. We argue that auditing generative AI requires evaluation frameworks that examine how synthetic populations systematically reshape demographic visibility across social roles.
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。
