# GenTUS: Simulating User Behaviour and Language in Task-oriented Dialogues with Generative Transformers

arXiv: https://arxiv.org/abs/2208.10817 · HTML: https://mlsanity.com/paper/2208.10817/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 36 references that are in the map.
- First posted on arXiv 23 Aug 2022.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [A Call for Clarity in Reporting BLEU Scores](https://mlsanity.com/paper/1804.08771/) (2018)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [Neural Belief Tracker: Data-Driven Dialogue State Tracking](https://mlsanity.com/paper/1606.03777/) (2016)
- [Semantically Conditioned LSTM-based Natural Language Generation for Spoken Dialogue Systems](https://mlsanity.com/paper/1508.01745/) (2015)
- [Few-shot Natural Language Generation for Task-Oriented Dialog](https://mlsanity.com/paper/2002.12328/) (2020)
- [ConvLab-2: An Open-Source Toolkit for Building, Evaluating, and Diagnosing Dialogue Systems](https://mlsanity.com/paper/2002.04793/) (2020)
- [Neural User Simulation for Corpus-based Policy Optimisation for Spoken Dialogue Systems](https://mlsanity.com/paper/1805.06966/) (2018)
- [A Sequence-to-Sequence Model for User Simulation in Spoken Dialogue Systems](https://mlsanity.com/paper/1607.00070/) (2016)
- [User Modeling for Task Oriented Dialogues](https://mlsanity.com/paper/1811.04369/) (2018)
- [Transferable Dialogue Systems and User Simulators](https://mlsanity.com/paper/2107.11904/) (2021)
- [SGD-X: A Benchmark for Robust Generalization in Schema-Guided Dialogue Systems](https://mlsanity.com/paper/2110.06800/) (2021)
- [Domain-independent User Simulation with Transformers for Task-oriented Dialogue Systems](https://mlsanity.com/paper/2106.08838/) (2021)
- [DialCrowd 2.0: A Quality-Focused Dialog System Crowdsourcing Toolkit](https://mlsanity.com/paper/2207.12551/) (2022)

## Built on by (most cited first, 23 of 23)

- [Reliable LLM-based User Simulator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2402.13374/) (2024)
- [DuetSim: Building User Simulator with Dual Large Language Models for Task-Oriented Dialogues](https://mlsanity.com/paper/2405.13028/) (2024)
- [ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Format](https://mlsanity.com/paper/2211.17148/) (2022)
- [Goal Alignment in LLM-Based User Simulators for Conversational AI](https://mlsanity.com/paper/2507.20152/) (2025)
- [In-Context Learning User Simulators for Task-Oriented Dialog Systems](https://mlsanity.com/paper/2306.00774/) (2023)
- [User Simulation with Large Language Models for Evaluating Task-Oriented Dialogue](https://mlsanity.com/paper/2309.13233/) (2023)
- [Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning](https://mlsanity.com/paper/2507.17842/) (2025)
- [Personality-aware Student Simulation for Conversational Intelligent Tutoring Systems](https://mlsanity.com/paper/2404.06762/) (2024)
- [Large Language Models as User-Agents for Evaluating Task-Oriented-Dialogue Systems](https://mlsanity.com/paper/2411.09972/) (2024)
- [EmoUS: Simulating User Emotions in Task-Oriented Dialogues](https://mlsanity.com/paper/2306.01579/) (2023)
- [COMPASS: Benchmarking Constrained Optimization in LLM Agents](https://mlsanity.com/paper/2510.07043/) (2025)
- [Towards Goal-oriented Intelligent Tutoring Systems in Online Education](https://mlsanity.com/paper/2312.10053/) (2023)
- [Simulating Before Planning: Constructing Intrinsic User World Model for User-Tailored Dialogue Policy Planning](https://mlsanity.com/paper/2504.13643/) (2025)
- [Infusing Emotions into Task-oriented Dialogue Systems: Understanding, Management, and Generation](https://mlsanity.com/paper/2408.02417/) (2024)
- [DIAL: Direct Iterative Adversarial Learning for Realistic Multi-Turn Dialogue Simulation](https://mlsanity.com/paper/2512.20773/) (2025)
- [Interactive Text Generation](https://mlsanity.com/paper/2303.00908/) (2023)
- [Adversarial learning of neural user simulators for dialogue policy optimisation](https://mlsanity.com/paper/2306.00858/) (2023)
- [The Imperfect Learner: Incorporating Developmental Trajectories in Memory-based Student Simulation](https://mlsanity.com/paper/2511.05903/) (2025)
- [SayNext-Bench: Why Do LLMs Struggle with Next-Utterance Anticipation?](https://mlsanity.com/paper/2602.00327/) (2026)
- [Why Guided Dialog Policy Learning performs well? Understanding the role of adversarial learning and its alternative](https://mlsanity.com/paper/2307.06721/) (2023)
- [Pretrained Persona Mixture Models and Tandem Models for Human Simulation](https://mlsanity.com/paper/2609.22607/) (2026)
- [Proactive Dialogue Policy Optimization via Cognitive-State Transition](https://mlsanity.com/paper/2609.34948/) (2026)
- [SimInter: Evidence-Grounded User Simulation with Interview-Based Profile Enrichment for Conversational Recommender Systems](https://mlsanity.com/paper/2610.18308/) (2026)

## Abstract (arXiv)

User simulators (USs) are commonly used to train task-oriented dialogue systems (DSs) via reinforcement learning. The interactions often take place on semantic level for efficiency, but there is still a gap from semantic actions to natural language, which causes a mismatch between training and deployment environment. Incorporating a natural language generation (NLG) module with USs during training can partly deal with this problem. However, since the policy and NLG of USs are optimised separately, these simulated user utterances may not be natural enough in a given context. In this work, we propose a generative transformer-based user simulator (GenTUS). GenTUS consists of an encoder-decoder structure, which means it can optimise both the user policy and natural language generation jointly. GenTUS generates both semantic actions and natural language utterances, preserving interpretability and enhancing language variation. In addition, by representing the inputs and outputs as word sequences and by using a large pre-trained language model we can achieve generalisability in feature representation. We evaluate GenTUS with automatic metrics and human evaluation. Our results show that GenTUS generates more natural language and is able to transfer to an unseen ontology in a zero-shot fashion. In addition, its behaviour can be further shaped with reinforcement learning opening the door to training specialised user simulators.