arXiv cs.CL· Siddhesh Pawar, Arnav Arora, Dustin Wright, Dirk Hovy, Isabelle Augenstein·· 13 小时前AI 评分29
研究 LLM 中的多元文化价值选择偏差
Investigating Multi-Cultural Value Selection Biases in LLMs
AI 导读
研究在系统提示词中设定国家角色、并在用户轮次通过国家名称（显式线索）或查询语言（隐式线索）给出第二重身份线索时 LLM 的价值选择偏差。在 World Values Survey 多项选择探测中，语言线索对答案的偏移约为显式线索的三倍，但偏移方向背离对应国家的分布，显式线索也未稳定地将答案拉向所指国家。
正文 · 原文
Abstract:Large language models (LLMs) serve users whose cultural identities are multi-layered, yet cultural evaluations commonly reduce identity to one label. In this work, we study LLMs under simultaneous identity cues, with a country persona in the system prompt and a second identity signaled in the user turn, either by naming a country (explicit cue) or through the query language (implicit cue). We test World Values Survey (WVS) multiple-choice probing and open-ended sociopolitical generation. In multiple-choice probing, language cues shift answers about three times more than explicit cues but away from the associated country's distribution, and explicit cues do not consistently move answers toward the named country. Across 1.6 million open-ended responses, naming a country closes 30-44% of the gap to the model's own responses for that country, and explicit cues produce more differentiated value changes than language cues. Our results suggest that country and language cues should be evaluated as distinct signals rather than interchangeable proxies for culture.
| Comments: | 27 pages, 13 figures, 18 tables |
| Subjects: | Computation and Language (cs.CL) |
| ACM classes: | I.2.7 |
| Cite as: | arXiv:2610.31199 [cs.CL] |
| (or arXiv:2610.31199v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.31199 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Siddhesh Pawar [view email]
[v1]
Thu, 22 Oct 2026 12:46:22 UTC (422 KB)
来源：arXiv cs.CL · arxiv.org