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

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

1 Jun 2023arXiv:2306.00774archive 2025-07-28

Silvia Terragni, Modestas Filipavicius, Nghia Khau, Bruna Guedes, André Manso, Roland Mathis

This paper presents a novel application of large language models in user simulation for task-oriented dialog systems, specifically focusing on an in-context learning approach. By harnessing the power of these models, the proposed approach generates diverse utterances based on user goals and limited dialog examples. Unlike traditional simulators, this method eliminates the need for labor-intensive rule definition or extensive annotated data, making it more efficient and accessible. Additionally, an error analysis of the interaction between the user simulator and dialog system uncovers common mistakes, providing valuable insights into areas that require improvement. Our implementation is available at https://github.com/telepathylabsai/prompt-based-user-simulator.

PaperPDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

telepathylabsai/prompt-based-user-simulator officialmentioned on GitHubpytorch report
silviatti/prompt-based-user-simulator mentioned on GitHubpytorch report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Goal-Oriented Dialogue SystemsIn-Context LearningInteractive Evaluation of DialogTask-Oriented Dialogue SystemsUser Simulation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Flan-T5LLaMA

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections