AI RESEARCH
Affective Flow Language Model for Emotional Support Conversation
arXiv CS.AI
•
ArXi:2602.08826v2 Announce Type: replace-cross Large language models (LLMs) have been widely applied to emotional conversation (ESC). However, complex multi-turn remains challenging. This is because existing alignment schemes rely on sparse outcome-level signals, thus offering limited supervision for intermediate strategy decisions. To fill this gap, this paper proposes affective flow language model for emotional conversation (AFlow), a framework that