SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting

TL;DR

SGP-TOD leverages schema-guided prompting with large language models to build task-oriented dialog systems without training data, achieving state-of-the-art zero-shot performance and easy domain adaptation.

Contribution

Introduces a training-free, schema-guided prompting framework for task-oriented dialog systems using LLMs, enabling effortless development and adaptation.

Findings

Achieves SOTA zero-shot performance on multiple datasets.

Outperforms few-shot approaches significantly.

Easily adapts to new functionalities with schema updates.

Abstract

Building end-to-end task bots and maintaining their integration with new functionalities using minimal human efforts is a long-standing challenge in dialog research. Recently large language models (LLMs) have demonstrated exceptional proficiency in conversational engagement and adherence to instructions across various downstream tasks. In this work, we introduce SGP-TOD, Schema-Guided Prompting for building Task-Oriented Dialog systems effortlessly based on LLMs. Utilizing the symbolic knowledge -- task schema, we instruct fixed LLMs to generate appropriate responses on novel tasks, circumventing the need for training data. Specifically, SGP-TOD comprises three components: a LLM for engaging with users, a DST Prompter to aid the LLM with dialog state tracking, which is then used to retrieve database items, and a Policy Prompter to elicit proper responses adhering to the provided dialog policy. Experimental results on Multiwoz, RADDLE and STAR datasets show that our training-free strategy SGP-TOD, without any task-specific data, yields state-of-the-art (SOTA) zero-shot performance, greatly surpasses the few-shot approaches. In a domain-extension setting, SGP-TOD aptly adapts to new functionalities by merely adding supplementary schema rules. We make our code and data publicly available.