AI RESEARCH
Discourse Diversity in Multi-Turn Empathic Dialogue
arXiv CS.AI
•
ArXi:2604.11742v1 Announce Type: cross Large language models (LLMs) produce responses rated as highly empathic in single-turn settings (Ayers, 2023; Lee, 2024), yet they are also known to be formulaic generators that reuse the same lexical patterns, syntactic templates, and dis