Task-Oriented Dialogue with In-Context Learning

Tom Bocklisch, Thomas Werkmeister, Daksh Varshneya, Alan Nichol
2/19/2024
cs.CL

No official code found. Best implementation: RasaHQ/tod-in-context-learning (38 stars, last commit 2024-02-20).

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.

View on arXivView PDF

Code Implementations(1)

RasaHQ/tod-in-context-learningCommunity100%
386Shell, PythonJan 31, 20242 years ago

Similar Papers

Injecting Salesperson's Dialogue Strategies in Large Language Models with Chain-of-Thought Reasoning

85% match2024

Conversation Routines: A Prompt Engineering Framework for Task-Oriented Dialog Systems

85% match2025

In-Context Learning User Simulators for Task-Oriented Dialog Systems

84% match1 repo292023

Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems

83% match2024

Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models

83% match1 repo232024

Reasoning in Conversation: Solving Subjective Tasks through Dialogue Simulation for Large Language Models

83% match2024

Cite this paper

@article{bocklisch2024taskoriented,
  title  = {Task-Oriented Dialogue with In-Context Learning},
  author = {Tom Bocklisch and Thomas Werkmeister and Daksh Varshneya and Alan Nichol},
  year   = {2024},
  eprint = {2402.12234},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.12234v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.12234.svg)](https://codeofpaper.com/paper/2402.12234)

Discussion