Cause-Aware Empathetic Response Generation via Chain-of-Thought Fine-Tuning
This addresses the problem of limited affective understanding in dialogue agents for human-computer interaction, but it is incremental as it builds on existing methods with a novel integration.
The paper tackled empathetic response generation by integrating emotion cause reasoning via Chain-of-Thought fine-tuning on LLMs, achieving state-of-the-art performance on a benchmark dataset with LLaMA-7b.
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.