构建首个跨文化情感支持数据集，提升大模型的文化敏感性。
Tailored Emotional LLM-Supporter: Enhancing Cultural Sensitivity
- 设计文化感知提示策略，引导大模型生成跨文化共情回应。
- 实测表明优化后模型表现优于匿名网友，且文化角色扮演无效。
- 适用于心理治疗培训，助力新手提升文化胜任力。
大型语言模型在提供情感支持和生成共情回应方面展现出潜力，但其文化敏感性仍缺乏系统研究。本文提出CultureCare，首个面向该任务的数据集，涵盖四种文化，包含1729条困境消息、1523个文化信号和1041种支持策略，并附有细粒度的情绪与文化标注。基于此，我们（i）设计并测试了四种适应策略，用于引导三种先进大模型生成文化敏感回应；（ii）通过大模型评阅、在地人类标注者及临床心理学家进行综合评估；（iii）证明经优化的模型表现优于匿名在线同龄人回复，且简单文化角色扮演无法实现真正敏感；（iv）探索大模型在临床训练中的应用，专家认为其有助于培养新手治疗师的文化胜任力。
原文摘要 · Abstract (English)
Large language models (LLMs) show promise in offering emotional support and generating empathetic responses for individuals in distress, but their ability to deliver culturally sensitive support remains underexplored due to a lack of resources. In this work, we introduce CultureCare, the first dataset designed for this task, spanning four cultures and including 1729 distress messages, 1523 cultural signals, and 1041 support strategies with fine-grained emotional and cultural annotations. Leveraging CultureCare, we (i) develop and test four adaptation strategies for guiding three state-of-the-art LLMs toward culturally sensitive responses; (ii) conduct comprehensive evaluations using LLM-as-a-Judge, in-culture human annotators, and clinical psychologists; (iii) show that adapted LLMs outperform anonymous online peer responses, and that simple cultural role-play is insufficient for cultural sensitivity; and (iv) explore the application of LLMs in clinical training, where experts highlight their potential in fostering cultural competence in novice therapists.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。