# User Simulation with Large Language Models for Evaluating Task-Oriented Dialogue

arXiv: https://arxiv.org/abs/2309.13233 · HTML: https://mlsanity.com/paper/2309.13233/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 34 references that are in the map.
- First posted on arXiv 23 Sep 2023.

## Builds on (most cited first, 21 of 21)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [BLOOM: A 176B-Parameter Open-Access Multilingual Language Model](https://mlsanity.com/paper/2211.05100/) (2022)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [GPT-NeoX-20B: An Open-Source Autoregressive Language Model](https://mlsanity.com/paper/2204.06745/) (2022)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Multi-Task Pre-Training for Plug-and-Play Task-Oriented Dialogue System](https://mlsanity.com/paper/2109.14739/) (2021)
- [SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching](https://mlsanity.com/paper/2005.05298/) (2020)
- [AlexaTM 20B: Few-Shot Learning Using a Large-Scale Multilingual Seq2Seq Model](https://mlsanity.com/paper/2208.01448/) (2022)
- [ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems](https://mlsanity.com/paper/2002.04793/) (2020)
- [How to Build User Simulators to Train RL-based Dialog Systems](https://mlsanity.com/paper/1909.01388/) (2019)
- [Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructions](https://mlsanity.com/paper/2010.10216/) (2020)
- [GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers](https://mlsanity.com/paper/2208.10817/) (2022)
- [Is MultiWOZ a Solved Task? An Interactive TOD Evaluation Framework with User Simulator](https://mlsanity.com/paper/2210.14529/) (2022)
- [Metaphorical User Simulators for Evaluating Task-oriented Dialogue Systems](https://mlsanity.com/paper/2204.00763/) (2022)
- [Teaching Models new APIs: Domain-Agnostic Simulators for Task Oriented Dialogue](https://mlsanity.com/paper/2110.06905/) (2021)
- [How to Evaluate Your Dialogue Models: A Review of Approaches](https://mlsanity.com/paper/2108.01369/) (2021)

## Built on by (most cited first, 19 of 19)

- [Mind the Sim2Real Gap in User Simulation for Agentic Tasks](https://mlsanity.com/paper/2603.11245/) (2026)
- [Goal Alignment in LLM-Based User Simulators for Conversational AI](https://mlsanity.com/paper/2507.20152/) (2025)
- [Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems](https://mlsanity.com/paper/2411.09972/) (2024)
- [Quantifying the Utility of User Simulators for Building Collaborative LLM Assistants](https://mlsanity.com/paper/2605.09808/) (2026)
- [UserLM-R1: Modeling Human Reasoning in User Language Models with Multi-Reward Reinforcement Learning](https://mlsanity.com/paper/2601.09215/) (2026)
- [Learning User Simulators with Turing Rewards](https://mlsanity.com/paper/2606.19336/) (2026)
- [Simulating User Agents for Embodied Conversational-AI](https://mlsanity.com/paper/2410.23535/) (2024)
- [Measuring and Mitigating the Distributional Gap Between Real and Simulated User Behaviors](https://mlsanity.com/paper/2605.07847/) (2026)
- [Reinforcing Human Behavior Simulation via Verbal Feedback](https://mlsanity.com/paper/2605.20506/) (2026)
- [SCICONVBENCH: Benchmarking LLMs on Multi-Turn Clarification for Task Formulation in Computational Science](https://mlsanity.com/paper/2605.18630/) (2026)
- [Agentic Persona Control and Task State Tracking for Realistic User Simulation in Interactive Scenarios](https://mlsanity.com/paper/2601.15290/) (2025)
- [SayNext-Bench: Why Do LLMs Struggle with Next-Utterance Anticipation?](https://mlsanity.com/paper/2602.00327/) (2026)
- [Controllable User Simulation](https://mlsanity.com/paper/2605.11519/) (2026)
- [EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents](https://mlsanity.com/paper/2605.27820/) (2026)
- [Mind2Dialogue: Training Human-Aware Language Models by Simulating User Mental States](https://mlsanity.com/paper/2609.15972/) (2026)
- [From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs](https://mlsanity.com/paper/2604.14137/) (2026)
- [CustomerSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators](https://mlsanity.com/paper/2605.08334/) (2026)
- [User-Aware Active Knowledge Acquisition for Emotional Support Dialogue](https://mlsanity.com/paper/2605.29715/) (2026)
- [Large-Scale ChatBot Validation Through Customer Digital Twin Simulations](https://mlsanity.com/paper/2607.26060/) (2026)

## Abstract (arXiv)

One of the major impediments to the development of new task-oriented dialogue (TOD) systems is the need for human evaluation at multiple stages and iterations of the development process. In an effort to move toward automated evaluation of TOD, we propose a novel user simulator built using recently developed large pretrained language models (LLMs). In order to increase the linguistic diversity of our system relative to the related previous work, we do not fine-tune the LLMs used by our system on existing TOD datasets; rather we use in-context learning to prompt the LLMs to generate robust and linguistically diverse output with the goal of simulating the behavior of human interlocutors. Unlike previous work, which sought to maximize goal success rate (GSR) as the primary metric of simulator performance, our goal is a system which achieves a GSR similar to that observed in human interactions with TOD systems. Using this approach, our current simulator is effectively able to interact with several TOD systems, especially on single-intent conversational goals, while generating lexically and syntactically diverse output relative to previous simulators that rely upon fine-tuned models. Finally, we collect a Human2Bot dataset of humans interacting with the same TOD systems with which we experimented in order to better quantify these achievements.