DiagGPT: An LLM-based and Multi-agent Dialogue System with Automatic Topic Management for Flexible Task-Oriented Dialogue

TL;DR

DiagGPT is a novel LLM-based multi-agent dialogue system designed to improve task-oriented dialogue by automatically managing topics and guiding users toward goal completion, especially in complex diagnostic scenarios.

Contribution

This paper introduces DiagGPT, an innovative LLM extension that enhances task-oriented dialogue with automatic topic management for more flexible and effective user interactions.

Findings

Outperforms existing models in task-oriented dialogue tasks

Effectively manages dialogue topics throughout interactions

Demonstrates potential for practical applications in specialized fields

Abstract

A significant application of Large Language Models (LLMs), like ChatGPT, is their deployment as chat agents, which respond to human inquiries across a variety of domains. While current LLMs proficiently answer general questions, they often fall short in complex diagnostic scenarios such as legal, medical, or other specialized consultations. These scenarios typically require Task-Oriented Dialogue (TOD), where an AI chat agent must proactively pose questions and guide users toward specific goals or task completion. Previous fine-tuning models have underperformed in TOD and the full potential of conversational capability in current LLMs has not yet been fully explored. In this paper, we introduce DiagGPT (Dialogue in Diagnosis GPT), an innovative approach that extends LLMs to more TOD scenarios. In addition to guiding users to complete tasks, DiagGPT can effectively manage the status of all topics throughout the dialogue development. This feature enhances user experience and offers a more flexible interaction in TOD. Our experiments demonstrate that DiagGPT exhibits outstanding performance in conducting TOD with users, showing its potential for practical applications in various fields.