ReflectDiffu:Reflect between Emotion-intent Contagion and Mimicry for Empathetic Response Generation via a RL-Diffusion Framework

TL;DR

ReflectDiffu is a lightweight framework that enhances empathetic response generation by integrating emotion contagion, intent mimicry, and reinforcement learning within a diffusion model, achieving state-of-the-art results.

Contribution

It introduces a novel RL-Diffusion framework that models emotion and intent interplay for more controllable and empathetic responses, addressing limitations of prior large language models.

Findings

Outperforms existing models in relevance and empathy

Achieves state-of-the-art automatic evaluation scores

Demonstrates improved human evaluation results

Abstract

Empathetic response generation necessitates the integration of emotional and intentional dynamics to foster meaningful interactions. Existing research either neglects the intricate interplay between emotion and intent, leading to suboptimal controllability of empathy, or resorts to large language models (LLMs), which incur significant computational overhead. In this paper, we introduce ReflectDiffu, a lightweight and comprehensive framework for empathetic response generation. This framework incorporates emotion contagion to augment emotional expressiveness and employs an emotion-reasoning mask to pinpoint critical emotional elements. Additionally, it integrates intent mimicry within reinforcement learning for refinement during diffusion. By harnessing an intent twice reflect mechanism of Exploring-Sampling-Correcting, ReflectDiffu adeptly translates emotional decision-making into precise intent actions, thereby addressing empathetic response misalignments stemming from emotional misrecognition. Through reflection, the framework maps emotional states to intents, markedly enhancing both response empathy and flexibility. Comprehensive experiments reveal that ReflectDiffu outperforms existing models regarding relevance, controllability, and informativeness, achieving state-of-the-art results in both automatic and human evaluations.