Show, Don't Tell: Demonstrations Outperform Descriptions for Schema-Guided Task-Oriented Dialogue

TL;DR

This paper introduces a method called Show, Don't Tell that uses example dialogues instead of descriptions to teach large language models schema semantics, significantly improving zero-shot dialogue state tracking performance.

Contribution

The work demonstrates that using labeled example dialogues as schema representations outperforms traditional description-based methods in zero-shot dialogue systems.

Findings

Achieves state-of-the-art results on Schema-Guided Dialogue and MultiWOZ benchmarks.

Shows that example-based prompts improve zero-shot generalization.

Requires similar effort from developers as creating descriptions.

Abstract

Building universal dialogue systems that operate across multiple domains/APIs and generalize to new ones with minimal overhead is a critical challenge. Recent works have leveraged natural language descriptions of schema elements to enable such systems; however, descriptions only indirectly convey schema semantics. In this work, we propose Show, Don't Tell, which prompts seq2seq models with a labeled example dialogue to show the semantics of schema elements rather than tell the model through descriptions. While requiring similar effort from service developers as generating descriptions, we show that using short examples as schema representations with large language models results in state-of-the-art performance on two popular dialogue state tracking benchmarks designed to measure zero-shot generalization - the Schema-Guided Dialogue dataset and the MultiWOZ leave-one-out benchmark.