Scholarlink

Emotional Support Conversation (ESC) aims to ease a help-seeker’ psychological distress through dialogue with a supporter. We propose CasDecNet (Cascading Fusion-Guided Decoding Network), a novel response generation model that enhances empathy in three stages: understanding context, acquiring cognitive and affective empathy, and incorporating strategic support. Our model uses multi-dimensional external knowledge to better infer the user’s situation and implement empathy effectively. Experiments on the ESConv dataset show that CasDecNet outperforms baselines in both automatic and LLM-based evaluations, especially in terms of response diversity and empathy, indicating its promise for human-like emotional support.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Empathetic Response Generation in Emotional Support Conversation via Multi-stage Cascading Information Fusion

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Jianwei Zhang,
  • Shota Sato,
  • Yuta Sasaki,
  • Yuhki Shiraishi

摘要

Emotional Support Conversation (ESC) aims to ease a help-seeker’ psychological distress through dialogue with a supporter. We propose CasDecNet (Cascading Fusion-Guided Decoding Network), a novel response generation model that enhances empathy in three stages: understanding context, acquiring cognitive and affective empathy, and incorporating strategic support. Our model uses multi-dimensional external knowledge to better infer the user’s situation and implement empathy effectively. Experiments on the ESConv dataset show that CasDecNet outperforms baselines in both automatic and LLM-based evaluations, especially in terms of response diversity and empathy, indicating its promise for human-like emotional support.