AI写共情回复很受欢迎，但套路化严重。
AI generates well-liked but templatic empathic responses
- 分析10种共情语言策略，发现AI高度依赖固定模板。
- 90%的AI回复匹配同一套策略组合，覆盖81%-92%内容。
- 适合关注AI共情机制与人机交互的研究者阅读。
越来越多的人开始使用大语言模型（LLMs）获取情感支持，且人们认为其回应比人类写的更具同理心。我们提出一个原因：LLMs 学会并持续使用一种广受喜爱的共情表达模板。我们构建了包含10种共情语言策略的分类体系，涵盖确认感受、复述等，并用于分析人类与LLM生成的共情回复。在两项研究中，共比较了n=3,265条由六种模型生成的AI回复和n=1,290条人工撰写回复。结果显示，LLM回复在语篇功能层面高度程式化。我们发现一套模板——一系列策略的结构化序列——可匹配83%–90%的AI回复（在独立样本中为60%–83%），且当匹配时，覆盖了81%–92%的回复内容。相比之下，人类回复更具多样性。最后讨论了该发现对人工智能共情未来的启示。
原文摘要 · Abstract (English)
Recent research shows that greater numbers of people are turning to Large Language Models (LLMs) for emotional support, and that people rate LLM responses as more empathic than human-written responses. We suggest a reason for this success: LLMs have learned and consistently deploy a well-liked template for expressing empathy. We develop a taxonomy of 10 empathic language "tactics" that include validating someone's feelings and paraphrasing, and apply this taxonomy to characterize the language that people and LLMs produce when writing empathic responses. Across a set of 2 studies comparing a total of n = 3,265 AI-generated (by six models) and n = 1,290 human-written responses, we find that LLM responses are highly formulaic at a discourse functional level. We discovered a template -- a structured sequence of tactics -- that matches between 83--90% of LLM responses (and 60--83\% in a held out sample), and when those are matched, covers 81--92% of the response. By contrast, human-written responses are more diverse. We end with a discussion of implications for the future of AI-generated empathy.
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。