重复社交互动中的文化适应
Cultural Adaptation within Repeated Social Interactions
Chen Cecilia Liu · Roi Reichart · Anna Korhonen
中文摘要
人类文化中大量内容属于隐性知识，通常通过情境化社交互动习得。随着 LLM 作为交互式智能体部署到多元社区，评估其文化能力需要超越现有的问答方法，从“知道什么”转向“如何适应”。本工作拓宽 NLP 中文化适应的研究范围，通过沙盒环境考察 LLM 能否在重复互动中实现适应。将文化适应重新定义为通过社交互动持续同化规范的过程，研究表明记忆机制促进跨重复互动的纵向学习，支持向不同社交场景迁移，并在五种语言上实现多语言规范同化。这些发现为 LLM 中持续、互动驱动的文化适应奠定基础。
关键要点
- 01现有问答式评估无法衡量 LLM 在互动中的文化适应能力
- 02用沙盒环境让 LLM 通过重复社交互动学习隐性文化规范
- 03记忆机制支持纵向学习、跨场景迁移与五种语言规范同化
- 04将文化适应重新定义为持续同化规范的过程，而非静态知识考察
解读
尚无解读。
原始英文摘要
arXiv:2611.08334v1 Announce Type: new Abstract: Much of human culture is tacit and is typically learned through situated social interaction. As LLMs are deployed as interactive agents across diverse communities, assessing their cultural competence demands moving beyond existing question-answering approaches, shifting from what they know to how they adapt. In this work, we broaden the scope of cultural adaptation in NLP by investigating whether LLMs can adapt through repeated interactions via a sandbox environment. By reframing cultural adaptation as a continuous process of norm assimilation through social interaction, our work demonstrates that memory mechanisms foster longitudinal learning across repeated interactions, facilitate transfer to different social settings, and enable multilingual norm assimilation across five languages. Together, our findings lay the groundwork for continuous, interaction-driven cultural adaptation in LLMs.