Scholarlink

This research considers the task of automatically adding empathic headers (e.g., “Sorry to hear that.”) to agent responses in customer support conversations. We employ a task-oriented dialogue (TOD) response selection model which allows response headers to be selected from existing corpora of conversations. Since the model is not fine-tuned with information about emotions in tweets, it is supplemented by filtering based on emotion annotations. The open-sourced LLM Llama 3.1 is employed for providing these annotations. We devise an experiment to evaluate this approach by automatic means. The preliminary results are discussed.

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

Selecting Empathic Response Headers in Customer Support Conversations with LLM-Based Emotion Recognition

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • W. L. Yeung

摘要

This research considers the task of automatically adding empathic headers (e.g., “Sorry to hear that.”) to agent responses in customer support conversations. We employ a task-oriented dialogue (TOD) response selection model which allows response headers to be selected from existing corpora of conversations. Since the model is not fine-tuned with information about emotions in tweets, it is supplemented by filtering based on emotion annotations. The open-sourced LLM Llama 3.1 is employed for providing these annotations. We devise an experiment to evaluate this approach by automatic means. The preliminary results are discussed.