Reasoning before Responding: Integrating Commonsense-based Causality Explanation for Empathetic Response Generation

TL;DR

This paper introduces a novel approach for empathetic response generation that incorporates commonsense causality explanations from both user and system perspectives, improving response quality.

Contribution

It presents a new method integrating commonsense causality reasoning for both user and system perspectives into empathetic response generation, enhancing existing models like ChatGPT.

Findings

Outperforms baseline models in automatic evaluations

Achieves higher human evaluation scores

Enhances reasoning capabilities of ChatGPT

Abstract

Recent approaches to empathetic response generation try to incorporate commonsense knowledge or reasoning about the causes of emotions to better understand the user's experiences and feelings. However, these approaches mainly focus on understanding the causalities of context from the user's perspective, ignoring the system's perspective. In this paper, we propose a commonsense-based causality explanation approach for diverse empathetic response generation that considers both the user's perspective (user's desires and reactions) and the system's perspective (system's intentions and reactions). We enhance ChatGPT's ability to reason for the system's perspective by integrating in-context learning with commonsense knowledge. Then, we integrate the commonsense-based causality explanation with both ChatGPT and a T5-based model. Experimental evaluations demonstrate that our method outperforms other comparable methods on both automatic and human evaluations.