Rational Sensibility: LLM Enhanced Empathetic Response Generation Guided by Self-presentation Theory

TL;DR

This paper introduces a novel LLM-based empathetic response generation model guided by self-presentation theory, focusing on rationality and sensibility to improve human-like empathy in conversations.

Contribution

It proposes an innovative encoder module inspired by self-presentation theory and employs LLMs as rational brains to enhance empathetic responses.

Findings

Outperforms existing methods in automatic evaluations

Achieves higher scores in human assessments

Effectively balances sensibility and rationality in responses

Abstract

The development of Large Language Models (LLMs) provides human-centered Artificial General Intelligence (AGI) with a glimmer of hope. Empathy serves as a key emotional attribute of humanity, playing an irreplaceable role in human-centered AGI. Despite numerous researches aim to improve the cognitive empathy of models by incorporating external knowledge, there has been limited attention on the sensibility and rationality of the conversation itself, which are vital components of the empathy. However, the rationality information within the conversation is restricted, and previous methods of extending knowledge are subject to semantic conflict and single-role view. In this paper, we design an innovative encoder module inspired by self-presentation theory in sociology, which specifically processes sensibility and rationality sentences in dialogues. And we employ a LLM as a rational brain to decipher profound logical information preserved within the conversation, which assists our model in assessing the balance between sensibility and rationality to produce high-quality empathetic response. Experimental results demonstrate that our model outperforms other methods in both automatic and human evaluations.