Towards LLM-driven Dialogue State Tracking
This addresses the need for accurate DST in task-oriented dialogue systems while overcoming ChatGPT's limitations like closed-source nature and privacy concerns.
The paper tackles Dialogue State Tracking (DST) by evaluating ChatGPT's capabilities and developing LDST, an open-source framework using smaller foundation models with domain-slot instruction tuning, achieving performance comparable to ChatGPT and showing significant improvements over previous state-of-the-art methods in zero-shot and few-shot settings.
Dialogue State Tracking (DST) is of paramount importance in ensuring accurate tracking of user goals and system actions within task-oriented dialogue systems. The emergence of large language models (LLMs) such as GPT3 and ChatGPT has sparked considerable interest in assessing their efficacy across diverse applications. In this study, we conduct an initial examination of ChatGPT's capabilities in DST. Our evaluation uncovers the exceptional performance of ChatGPT in this task, offering valuable insights to researchers regarding its capabilities and providing useful directions for designing and enhancing dialogue systems. Despite its impressive performance, ChatGPT has significant limitations including its closed-source nature, request restrictions, raising data privacy concerns, and lacking local deployment capabilities. To address these concerns, we present LDST, an LLM-driven DST framework based on smaller, open-source foundation models. By utilizing a novel domain-slot instruction tuning method, LDST achieves performance on par with ChatGPT. Comprehensive evaluations across three distinct experimental settings, we find that LDST exhibits remarkable performance improvements in both zero-shot and few-shot setting compared to previous SOTA methods. The source code is provided for reproducibility.