mlsanityData to 7 Oct 2026

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

arXiv 2306.00774 ↗First posted 1 Jun 2023cs.CL cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 29 of its 45 references that are in the map. First posted on arXiv 1 Jun 2023.

Builds on

29 of 45 references.

References · 29

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2022Scaling Instruction-Finetuned Language Modelscited by 2,997
  5. 2019The Curious Case of Neural Text Degenerationcited by 2,881
  6. 2022Survey of Hallucination in Natural Language Generationcited by 2,056
  7. 2020Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inferencecited by 934
  8. 2020It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learnerscited by 668
  9. 2015Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systemscited by 134
  10. 2019Evaluating the State-of-the-Art of End-to-End Natural Language Generation: The E2E NLG Challengecited by 86
  11. 2020Recent Advances and Challenges in Task-oriented Dialog Systemcited by 78
  12. 2023Eight Things to Know about Large Language Modelscited by 73
17 more
  1. 2021Few-Shot Bot: Prompt-Based Learning for Dialogue Systemscited by 64
  2. 2020ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systemscited by 52
  3. 2021Shades of BLEU, Flavours of Success: The Case of MultiWOZcited by 48
  4. 2018Neural User Simulation for Corpus-based Policy Optimisation for Spoken Dialogue Systemscited by 42
  5. 2022Controllable Dialogue Simulation with In-Context Learningcited by 42
  6. 2020Language Models as Few-Shot Learner for Task-Oriented Dialogue Systemscited by 41
  7. 2016A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systemscited by 39
  8. 2018User Modeling for Task Oriented Dialoguescited by 36
  9. 2022Evaluating Mixed-initiative Conversational Search Systems via User Simulationcited by 24
  10. 2021Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systemscited by 23
  11. 2022GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformerscited by 22
  12. 2022ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Formatcited by 22
  13. 2022Dialogue Summaries as Dialogue States (DS2), Template-Guided Summarization for Few-shot Dialogue State Trackingcited by 21
  14. 2023An In-depth Investigation of User Response Simulation for Conversational Searchcited by 20
  15. 2021Few Shot Dialogue State Tracking using Meta-learningcited by 16
  16. 2022Is MultiWOZ a Solved Task? An Interactive TOD Evaluation Framework with User Simulatorcited by 15
  17. 2022A Generative User Simulator with GPT-based Architecture and Goal State Tracking for Reinforced Multi-Domain Dialog Systemscited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 3; 2026: 8.

19 papers.

Sort:

By area:

  1. 2024Reliable LLM-based User Simulator for Task-Oriented Dialogue Systemscited by 24
  2. 2024A Survey on Recent Advances in Conversational Data Generationcited by 23
  3. 2024DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialoguescited by 23
  4. 2026A Survey on LLM-based Conversational User Simulationcited by 14
  5. 2024Personality-aware Student Simulation for Conversational Intelligent Tutoring Systemscited by 11
  6. 2024ProductAgent: Benchmarking Conversational Product Search Agent with Asking Clarification Questionscited by 10
  7. 2026ConvApparel: A Benchmark Dataset and Validation Framework for User Simulators in Conversational Recommenderscited by 10
  8. 2024Concept -- An Evaluation Protocol on Conversational Recommender Systems with System-centric and User-centric Factorscited by 9
  9. 2026Quantifying the Utility of User Simulators for Building Collaborative LLM Assistantscited by 6
  10. 2024Game Development as Human-LLM Interactioncited by 4
  11. 2025Exploring the Impact of Personality Traits on Conversational Recommender Systems: A Simulation with Large Language Modelscited by 4
  12. 2024From Intents to Conversations: Generating Intent-Driven Dialogues with Contrastive Learning for Multi-Turn Classificationcited by 2
7 more
  1. 2025VicSim: Enhancing Victim Simulation with Emotional and Linguistic Fidelitycited by 0
  2. 2025Improving Multi-turn Task Completion in Task-Oriented Dialog Systems via Prompt Chaining and Fine-Grained Feedbackcited by 0
  3. 2026FloCA: Towards Faithful and Logically Consistent Flowchart Reasoningcited by 0
  4. 2026Generating Diverse Personas for User Simulators to Test Interview Dialogue Systemscited by 0
  5. 2026"Act Like a 5th Grader" is Not Enough: Bounding Knowledge in LLM-Based User Simulatorscited by 0
  6. 2026Pretrained Persona Mixture Models and Tandem Models for Human Simulationcited by 0
  7. 2026UXBench Pro: Benchmarking Personalized User Experience in Multi-Turn Dialogue Interactionscited by 0