Empathetic Response in Audio-Visual Conversations Using Emotion Preference Optimization and MambaCompressor

TL;DR

This paper presents a novel approach combining Emotional Preference Optimization and MambaCompressor to improve empathetic response generation and conversation management in audio-visual chatbots, addressing nuanced understanding and long dialogue challenges.

Contribution

The study introduces Emotional Preference Optimization for nuanced response training and MambaCompressor for efficient dialogue history management, advancing empathetic chatbot capabilities.

Findings

Outperforms existing models in empathetic response quality

Reduces computational complexity in managing long conversations

Enhances contextual understanding in audio-visual chatbots

Abstract

Chatbot research is advancing with the growing importance of chatbots in fields that require human interactions, such as customer support and mental health care. Despite these advancements, chatbots still face significant challenges in understanding subtle nuances and managing long conversation histories. To address these issues, our study introduces a dual approach: firstly, we employ Emotional Preference Optimization (EPO) to train chatbots not only with correct responses but also with counter-emotional responses-those that are contextually similar but emotionally divergent. This training enables the model to discern fine nuance distinctions between correct and counter-emotional responses, thereby enhancing the quality of its responses. Secondly, we introduce MambaCompressor to effectively compress and manage extensive conversation histories, significantly reducing time and memory complexities while improving the chatbot's contextual understanding. Our comprehensive experiments across multiple datasets demonstrate that our model significantly outperforms existing models in generating empathetic responses and efficiently managing lengthy dialogues.