Task-Oriented Dialogue with In-Context Learning

TL;DR

This paper presents a task-oriented dialogue system leveraging large language models' in-context learning to translate conversations into a domain-specific language, simplifying development and enhancing handling of complex dialogues.

Contribution

It introduces a novel approach combining LLMs with deterministic business logic, reducing development effort and improving scalability over traditional intent-based systems.

Findings

Requires less development effort than traditional methods

Successfully handles complex dialogues challenging for NLU-based systems

Scales effectively to many tasks

Abstract

We describe a system for building task-oriented dialogue systems combining the in-context learning abilities of large language models (LLMs) with the deterministic execution of business logic. LLMs are used to translate between the surface form of the conversation and a domain-specific language (DSL) which is used to progress the business logic. We compare our approach to the intent-based NLU approach predominantly used in industry today. Our experiments show that developing chatbots with our system requires significantly less effort than established approaches, that these chatbots can successfully navigate complex dialogues which are extremely challenging for NLU-based systems, and that our system has desirable properties for scaling task-oriented dialogue systems to a large number of tasks. We make our implementation available for use and further study.