Presumed Cultural Identity: How Names Shape LLM Responses

TL;DR

This paper investigates how large language models (LLMs) exhibit cultural biases based on user names, revealing assumptions about identity that can reinforce stereotypes and impact personalized interactions.

Contribution

It provides an analysis of cultural presumptions in LLM responses related to user names, highlighting biases and suggesting improvements for nuanced personalization.

Findings

LLMs show strong cultural assumptions linked to names.

Names influence LLM responses across multiple cultures.

Biases can reinforce stereotypes in personalized interactions.

Abstract

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.