DiagGPT: An LLM-based Dialogue System with Automatic Topic Management for Goal-Oriented Dialogue

Anonymous

Abstract: Large Language Models (LLMs), such as ChatGPT, are becoming increasingly sophisticated, demonstrating capabilities that closely resemble those of humans. These AI models are playing an essential role in assisting humans with a wide array of tasks in daily life. A significant application of AI is its use as a chat agent, responding to human inquiries across various domains. Current LLMs have shown proficiency in answering general questions. However, basic question-answering dialogue often falls short in complex diagnostic scenarios, such as legal or medical consultations. These scenarios typically necessitate Goal-Oriented Dialogue (GOD), wherein an AI chat agent needs to proactively pose questions and guide users towards specific goals or task completion. Previous fine-tuning models have underperformed in GOD, and current LLMs do not inherently possess this capability. In this paper, we introduce DiagGPT (Dialogue in Diagnosis GPT), an innovative method that extends LLMs to GOD scenarios. Our experiments reveal that DiagGPT exhibits outstanding performance in conducting GOD with users, demonstrating its potential for practical applications in various fields.

Paper Type: long

Research Area: Dialogue and Interactive Systems

Contribution Types: NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: English

Consent To Share Submission Details: On behalf of all authors, we agree to the terms above to share our submission details.