假定的文化身份：名字如何影響大型語言模型的反應

Presumed Cultural Identity: How Names Shape LLM Responses

February 17, 2025

作者: Siddhesh Pawar, Arnav Arora, Lucie-Aimée Kaffee, Isabelle Augenstein

cs.AI

摘要

姓名與人類身份密切相關，它們可以作為個體性、文化傳承和個人歷史的標誌。然而，將姓名作為身份的核心指標可能會導致對複雜身份的過度簡化。在與大型語言模型（LLMs）互動時，用戶姓名是個性化的重要信息點。姓名可以通過直接用戶輸入（由聊天機器人請求）、作為任務上下文的一部分（如簡歷審查）或作為存儲用戶信息以實現個性化的內置記憶功能進入聊天機器人對話。我們通過測量LLMs在面對常見的尋求建議查詢時生成的回應中的文化假設，來研究與姓名相關的偏見，這些查詢可能涉及對用戶的假設。我們的分析表明，在多種文化的LLM生成中，存在與姓名相關的強烈文化身份假設。我們的工作對設計更細緻的個性化系統具有啟示意義，這些系統在保持有意義的定制的同時，避免強化刻板印象。

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.