用AI陪练提升人类共情表达能力，效果显著且不千篇一律。
Practicing with Language Models Cultivates Human Empathic Communication
- 让人类与扮演困境的AI对话，通过反馈提升共情表达。
- 3.4万条消息显示，人类虽有共情却难表达，干预后显著改善。
- 首次构建自然对话中个性化共情表达的分类体系，适合教育与心理领域。
共情是人际连接的核心，但人们常难以有效表达。在盲测中，大语言模型（LLMs）生成的回应常被评价为比人类写作更具共情力，但当回应被归因于AI时，接收者反而感觉更未被倾听。我们构建了一个对话平台，参与者需对扮演真实困境的LLM提供共情支持，并开展随机实验，收集了33,938条消息，涵盖968名参与者与他们的LLM对话伙伴之间的2,904轮文本对话。结果发现，参与者虽自述感受到共情，却系统性地未能有效表达；而基于个性化反馈的LLM教练干预显著提升了共情表达水平，且未导致回应趋同。此外，我们基于数据构建了自然对话中针对个人与职场困境的惯用共情表达分类体系。研究深化了对共情表达机制的理解，并展示了可扩展的、基于AI的共情培育方案。
原文摘要 · Abstract (English)
Empathy is central to human connection, yet people often struggle to express it effectively. In blinded evaluations, large language models (LLMs) generate responses that are often judged more empathic than human-written ones. Yet when a response is attributed to AI, recipients feel less heard than when comparable responses are attributed to a human. We built a conversation platform in which participants are asked to offer empathic support to an LLM expressing realistic troubles and conducted a randomized experiment collecting 33,938 messages spanning 2,904 text-based conversations between 968 participants and their LLM conversational partners. We find participants report feeling empathy but systematically fail to express it, but an LLM coaching intervention offering personalized feedback on effective empathic communication significantly boosts it without homogenizing participants' responses. Moreover, we derive a data-driven taxonomy of idiomatic empathic expressions in naturalistic dialogues across personal and workplace trouble scenarios. These results advance the scientific understanding of how empathy is expressed and demonstrate a scalable, AI-based intervention for scaffolding and cultivating it.
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。