Inference is All You Need: Self Example Retriever for Cross-domain Dialogue State Tracking with ChatGPT

TL;DR

This paper introduces a parameter-free, inference-based method using ChatGPT for cross-domain dialogue state tracking, enabling scalable and adaptable domain transfer without additional training.

Contribution

It presents a novel inference and in-context learning approach with ChatGPT for domain transfer in dialogue state tracking, eliminating the need for parameter updates.

Findings

Achieves competitive performance on MultiWOZ dataset

Demonstrates effective generalization across domains

Offers a scalable, parameter-free solution

Abstract

Traditional dialogue state tracking approaches heavily rely on extensive training data and handcrafted features, limiting their scalability and adaptability to new domains. In this paper, we propose a novel method that leverages inference and in-context learning with ChatGPT for domain transfer in dialogue state tracking, without any parameter updates. By guiding ChatGPT's chain of thought, we enable it to retrieve relevant examples and generalize knowledge to accurately infer dialogue states, solely through inference. Experimental results on the MultiWOZ dataset demonstrate competitive performance and promising generalization across domains. Our parameter-free approach offers a scalable and adaptable solution, opening new research directions in domain transfer learning.