发表机构
Massachusetts Institute of Technology（麻省理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究对比了母语使用者角色设定（NP）与目标语言生成后翻译（NL）两种跨语言引出策略对LLM人际建议的影响，发现二者不可互换，NP会改变建议的风格、可操作性及动作选择。
AI 中文摘要
大语言模型（LLM）越来越多地被用于人际建议，以及作为跨语言和文化研究社会行为的工具。引出语言或文化相关差异的常见捷径是要求模型以母语使用者的身份作答。我们测试这种母语使用者角色设定（NP）是否能复现模型以目标语言生成建议再将响应翻译回英文（NL）时得到的输出。我们使用涵盖13种语言、8个LLM的600个人际建议问题，对比NL与NP，测量语言风格、行为支架及强制选择动作建议。结果显示NP与NL不可互换：相比NL，NP常增加词汇社交线索（包括亲和性与积极语气），同时降低具体性、社交协调性等属性；NP在开放式建议中提供的可操作支架更少；在强制选择场景中，NP会改变模型选择的动作，更倾向对抗而非引导，效应量随语言、主题和模型变化。我们的结果表明，跨语言引出策略是重要的方法论选择，可改变建议的表述方式及模型推荐的动作。
英文摘要
LLMs are increasingly used for interpersonal advice and as tools for studying social behavior across languages and cultures. A common shortcut for eliciting language- or culture-related variation is to ask a model to answer as a native speaker. We test whether this native-speaker persona reproduces the outputs obtained when models instead generate advice in the target language and translate the response back into English. Using 600 interpersonal advice questions across 13 languages and eight LLMs, we compare native-language generation followed by translation (NL) with native-speaker persona prompting (NP), measuring linguistic style, behavioral scaffolding, and forced-choice action recommendations. We find that NP and NL are not interchangeable. Compared to NL, NP often increases lexical social cues, including affiliation and positive tone, while reducing qualities such as concreteness and social attunement; NP also provides less actionable scaffolding in open-ended advice. In forced-choice scenarios, NP changes which action the model selects, favoring confrontation over redirection, with effect sizes varying across languages, topics, and models. Our results show that cross-lingual elicitation strategy is a consequential methodological choice that can change both how advice is framed and which actions models recommend.
CommentsAccepted to EMNLP 2026 (Main Conference). 36 pages, 24 figures, 17 tables (9 pages main text; remainder references and appendices)
