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

Xiaoying Zhang, Baolin Peng, Kun LI, Jingyan Zhou, Helen M. Meng

Submission Type: Regular Long Paper

Submission Track: Dialogue and Interactive Systems

Submission Track 2: Theme Track: Large Language Models and the Future of NLP

Keywords: schema-guided LLM prompting, task bot, zero-shot dialog generation

TL;DR: We introduce SGP-TOD, Schema-Guided Prompting for building task bots effortlessly based on large language models, utilizing merely the predefined task schema.

Abstract: Building and maintaining end-to-end task bots using minimal human effort is a long-standing challenge in dialog research. In this work, we introduce SGP-TOD, Schema-Guided Prompting for building Task-Oriented Dialog systems effortlessly based on large language models (LLMs). Utilizing the predefined task schema, i.e., belief instruction and dialog policy, we instruct fixed LLMs to generate appropriate responses on novel tasks, without the need for training data. Specifically, SGP-TOD comprises three components: an LLM for interacting with users, a Dialog State Tracking (DST) Prompter to aid the LLM in tracking dialog states with the given belief instruction, and a Policy Prompter to direct the LLM to generate proper responses adhering to the provided dialog policy. Experimental results on Multiwoz, RADDLE, and STAR datasets show that our training-free strategy, SGP-TOD, yields state-of-the-art (SOTA) zero-shot performance, significantly surpassing 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.

Submission Number: 245