与语言模型练习培养人类共情沟通
Practicing with Language Models Cultivates Human Empathic Communication
AI总结：
研究通过实验平台探讨共情沟通技能的提升，发现简短的LLM指导干预能有效提升参与者与规范共情沟通模式的匹配度，并发现沉默共情效应。
摘要：
共情是人类连接的核心，但人们常难以有效表达。在盲评中，大语言模型（LLMs）生成的回应常被判断为比人类写的更共情。然而，当回应归因于AI时，接收者感觉不如归因于人类时被倾听和认可。为探索和解决这一共情沟通技能的差距，我们构建了Lend an Ear实验对话平台，参与者需向扮演个人和职场问题的LLM提供共情支持。从33,938条消息中提取出自然对话中的隐喻共情表达数据集。基于预先注册的随机实验，我们发现简短的LLM指导干预，提供个性化反馈以有效沟通共情，能显著提升参与者沟通模式与规范共情沟通模式的匹配度，相对于对照组和接受视频但非个性化反馈的组。此外，我们发现沉默共情效应：人们感觉共情但系统性地未能表达。然而，参与者能可靠地将符合规范共情沟通标准的回应视为更表达共情。这些结果推进了对共情如何表达和被重视的科学理解，并展示了可扩展的AI干预方法，用于构建和培养共情。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
