研究名字如何影响大模型对用户文化的误判
Presumed Cultural Identity: How Names Shape LLM Responses
- 用常见提问测试大模型对姓名的跨文化假设
- 多文化背景下均发现显著文化身份误判倾向
- 适合关注公平性与个性化设计的研究者
姓名与人类身份密切相关，可体现个体性、文化传承与个人历史。然而将姓名作为身份核心指标可能导致对复杂身份的过度简化。在与大模型交互时，用户姓名是个性化的重要信息来源，可通过直接输入、任务上下文（如简历评审）或内置记忆功能实现。本研究通过分析大模型在常见建议类查询中生成的回应，考察其对姓名相关的文化预设。结果表明，在多种文化背景下，大模型普遍存在基于姓名的文化身份假设。该研究对设计更细致、避免强化刻板印象的个性化系统具有重要意义。
原文摘要 · Abstract (English)
Names are deeply tied to human identity. They can serve as markers of individuality, cultural heritage, and personal history. However, using names as a core indicator of identity can lead to over-simplification of complex identities. When interacting with LLMs, user names are an important point of information for personalisation. Names can enter chatbot conversations through direct user input (requested by chatbots), as part of task contexts such as CV reviews, or as built-in memory features that store user information for personalisation. We study biases associated with names by measuring cultural presumptions in the responses generated by LLMs when presented with common suggestion-seeking queries, which might involve making assumptions about the user. Our analyses demonstrate strong assumptions about cultural identity associated with names present in LLM generations across multiple cultures. Our work has implications for designing more nuanced personalisation systems that avoid reinforcing stereotypes while maintaining meaningful customisation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。