两种身份的故事：对人类与AI生成角色画像的伦理审计
A Tale of Two Identities: An Ethical Audit of Human and AI-Crafted Personas
AI总结：
本文审计GPT4o、Gemini 1.5 Pro与Deepseek 2.5生成的1512个角色画像，揭示其对种族身份的过度凸显和叙事简化造成算法他者化，并提出评估与验证建议。
摘要：
随着LLM（大语言模型）越来越多地被用于生成合成角色画像，尤其是在健康、隐私和HCI等数据受限领域，理解这些叙事如何表征身份——特别是少数群体社区的身份——变得十分必要。在本文中，我们从表征性伤害的视角审计由3个LLM（GPT4o、Gemini 1.5 Pro、Deepseek 2.5）生成的合成角色画像，并特别聚焦种族身份。我们采用结合细读、词汇分析和参数化创造力框架的混合方法，将1512个LLM生成的角色画像与人类撰写的回答进行比较。研究发现表明，LLM不成比例地突出种族标记，过度生产具有文化编码的语言，并构建出句法繁复却在叙事上被简化的角色画像。这些模式导致一系列社会技术伤害，包括刻板印象、异国情调化、抹除和善意偏见，而这些伤害往往被表面上积极的叙述所掩盖。我们将这一现象形式化为算法他者化，即少数化身份被呈现得高度可见，却更不真实。基于这些发现，我们为面向合成身份生成的叙事感知评估指标和以社区为中心的验证协议提供设计建议。
英文摘要：
As LLMs (large language models) are increasingly used to generate synthetic personas particularly in data-limited domains such as health, privacy, and HCI, it becomes necessary to understand how these narratives represent identity, especially that of minority communities. In this paper, we audit synthetic personas generated by 3 LLMs (GPT4o, Gemini 1.5 Pro, Deepseek 2.5) through the lens of representational harm, focusing specifically on racial identity. Using a mixed methods approach combining close reading, lexical analysis, and a parameterized creativity framework, we compare 1512 LLM generated personas to human-authored responses. Our findings reveal that LLMs disproportionately foreground racial markers, overproduce culturally coded language, and construct personas that are syntactically elaborate yet narratively reductive. These patterns result in a range of sociotechnical harms, including stereotyping, exoticism, erasure, and benevolent bias, that are often obfuscated by superficially positive narrations. We formalize this phenomenon as algorithmic othering, where minoritized identities are rendered hypervisible but less authentic. Based on these findings, we offer design recommendations for narrative-aware evaluation metrics and community-centered validation protocols for synthetic identity generation.
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。
