基于思维链微调的因果感知共情回复生成
Cause-Aware Empathetic Response Generation via Chain-of-Thought Fine-Tuning
AI总结：
本文提出因果感知共情生成方法，通过在大语言模型上整合情感与原因的思维链提示及指令微调，并引入COMET外部知识，显著提升了LLaMA-7b的共情回复生成性能。
摘要：
共情回复生成赋予智能体理解对话上下文并对表达的情感做出反应的能力。以往的工作主要侧重于利用说话者的情感标签，却忽略了情感因果推理在共情回复生成中的重要性，这阻碍了模型进一步进行情感理解和认知推断的能力。在本文中，我们提出了一种因果感知的共情生成方法，通过在大语言模型（LLMs）上设计良好的思维链（CoT）提示来整合情感与原因。我们的方法可以通过指令微调并增强提示中共情倾听者的角色意识，极大地提升LLMs的共情表现。此外，我们提出将来自COMET的因果导向外部知识纳入提示中，这提高了生成的多样性，同时缓解了内部与外部知识之间的冲突。在基准数据集上的实验结果表明，我们的方法在LLaMA-7b上实现了在自动评估和人工评估中的最优性能。
英文摘要：
Empathetic response generation endows agents with the capability to comprehend dialogue contexts and react to expressed emotions. Previous works predominantly focus on leveraging the speaker's emotional labels, but ignore the importance of emotion cause reasoning in empathetic response generation, which hinders the model's capacity for further affective understanding and cognitive inference. In this paper, we propose a cause-aware empathetic generation approach by integrating emotions and causes through a well-designed Chain-of-Thought (CoT) prompt on Large Language Models (LLMs). Our approach can greatly promote LLMs' performance of empathy by instruction tuning and enhancing the role awareness of an empathetic listener in the prompt. Additionally, we propose to incorporate cause-oriented external knowledge from COMET into the prompt, which improves the diversity of generation and alleviates conflicts between internal and external knowledge at the same time. Experimental results on the benchmark dataset demonstrate that our approach on LLaMA-7b achieves state-of-the-art performance in both automatic and human evaluations.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
