Multi-Level Knowledge-Enhanced Prompting for Empathetic Dialogue Generation
Ziyin Gu, Qingmeng Zhu, Hao He, Zhipeng Yu, Tianxing Lan, Shuo Yuan · 2024
Empathetic dialogue systems can recognize users’ emotions and provide appropriate responses, which are crucial for enhancing the user experience. However, existing empathetic dialogue systems often fall short in understanding some complex implicit emotions. To address this problem, we propose a multi-level knowledge-enhanced prompting approach to achieve more effective empathetic dialogue generation effect. We first acquire topic words and emotional keywords as low-level emotional knowledge. Next, we retrieve dialogue samples that are most similar in topic and emotional attributes, forming mid-level emotional knowledge. Subsequently, we guide a large language model (LLM) to generate high-level comprehensive emotional knowledge based on the information from the previous two levels and the dialogue context. Finally, based on the emotional knowledge, we further guide LLM to generate empathetic responses. The research results indicate that our multi-level knowledge-enhanced prompting approach outperforms other baselines.