Rethinking Task-Oriented Dialogue Systems: From Complex Modularity to Zero-Shot Autonomous Agent

Anonymous

TL;DR: This paper presents AutoTOD, a zero-shot autonomous task-oriented dialogue agent that eliminates the need for complex modular components, relying solely on a general-purpose large language model. It shows superior task completion and language skills.

Abstract: Task-oriented dialogue (TOD) systems are predominantly designed to be composed of several functional modules (e.g. dialogue state tracker, dialogue policy, natural language generation) whether they are pipeline or end-to-end architectures. However, this modular design not only heavily relies on massive fully-annotated data, but also suffers from many intrinsic drawbacks, such as serious error accumulation, poor generalization ability, high customization cost, and low fault tolerance rate. In this paper, we rethink the architecture of the task-oriented dialogue systems and propose a novel fully zero-shot autonomous TOD agent, named AutoTOD, where all the delicate modules in traditional TOD systems are deprecated and all it needs is a general-purpose instruction-following language model (e.g. GPT-4). AutoTOD only leverages a simple instruction schema consisting of the description of tasks and external APIs, and can autonomously decide to what to do at each dialogue turn, including asking for information, calling APIs, summarizing API results, and correcting previous mistakes. Moreover, we propose a simulation-based evaluation framework to better validate the abilities of TOD models in real-life scenarios. Extensive experiments conducted on the MultiWOZ and SGD datasets show the superior task completion ability and flexible language skills of AutoTOD.

Paper Type: long

Research Area: Dialogue and Interactive Systems

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Approaches to low-resource settings, Approaches low compute settings-efficiency, Publicly available software and/or pre-trained models

Languages Studied: English