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

arXiv: https://arxiv.org/abs/2404.14772 · HTML: https://mlsanity.com/paper/2404.14772/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Conversational and speech RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 33 of its 44 references that are in the map.
- First posted on arXiv 23 Apr 2024.

## Placed in

- Retrieval-augmented generation / [Conversational and speech RAG](https://mlsanity.com/rag/conversational-and-speech-rag/)

## Builds on (most cited first, 30 of 33)

- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Ups and Downs: Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering](https://mlsanity.com/paper/1602.01585/) (2016)
- [Texygen: A Benchmarking Platform for Text Generation Models](https://mlsanity.com/paper/1802.01886/) (2018)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [Towards Deep Conversational Recommendations](https://mlsanity.com/paper/1812.07617/) (2018)
- [Taskmaster-1: Toward a Realistic and Diverse Dialog Dataset](https://mlsanity.com/paper/1909.05358/) (2019)
- [Task-Oriented Dialogue as Dataflow Synthesis](https://mlsanity.com/paper/2009.11423/) (2020)
- [UBAR: Towards Fully End-to-End Task-Oriented Dialog Systems with GPT-2](https://mlsanity.com/paper/2012.03539/) (2020)
- [Learning End-to-End Goal-Oriented Dialog](https://mlsanity.com/paper/1605.07683/) (2016)
- [Towards Topic-Guided Conversational Recommender System](https://mlsanity.com/paper/2010.04125/) (2020)
- [INSPIRED: Toward Sociable Recommendation Dialog Systems](https://mlsanity.com/paper/2009.14306/) (2020)
- [Frames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems](https://mlsanity.com/paper/1704.00057/) (2017)
- [Recent Advances and Challenges in Task-oriented Dialog System](https://mlsanity.com/paper/2003.07490/) (2020)
- [Are LLMs All You Need for Task-Oriented Dialogue?](https://mlsanity.com/paper/2304.06556/) (2023)
- [MultiDoc2Dial: Modeling Dialogues Grounded in Multiple Documents](https://mlsanity.com/paper/2109.12595/) (2021)
- [MAVE: A Product Dataset for Multi-source Attribute Value Extraction](https://mlsanity.com/paper/2112.08663/) (2021)
- [Recommendation as a Communication Game: Self-Supervised Bot-Play for Goal-oriented Dialogue](https://mlsanity.com/paper/1909.03922/) (2019)
- [Zero-Shot Anticipation for Instructional Activities](https://mlsanity.com/paper/1812.02501/) (2018)
- [Controllable Dialogue Simulation with In-Context Learning](https://mlsanity.com/paper/2210.04185/) (2022)
- [SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting](https://mlsanity.com/paper/2305.09067/) (2023)
- [Conversational Information Seeking](https://mlsanity.com/paper/2201.08808/) (2022)
- [Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk](https://mlsanity.com/paper/2401.05033/) (2024)
- [Fusing task-oriented and open-domain dialogues in conversational agents](https://mlsanity.com/paper/2109.04137/) (2021)
- [Simulated Chats for Building Dialog Systems: Learning to Generate Conversations from Instructions](https://mlsanity.com/paper/2010.10216/) (2020)
- [User Memory Reasoning for Conversational Recommendation](https://mlsanity.com/paper/2006.00184/) (2020)
- [End-to-end Task-oriented Dialogue: A Survey of Tasks, Methods, and Future Directions](https://mlsanity.com/paper/2311.09008/) (2023)
- [Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems](https://mlsanity.com/paper/2104.09088/) (2021)
- [Talk the Walk: Synthetic Data Generation for Conversational Music Recommendation](https://mlsanity.com/paper/2301.11489/) (2023)

## Built on by (most cited first, 6 of 6)

- [A Survey on Recent Advances in Conversational Data Generation](https://mlsanity.com/paper/2405.13003/) (2024)
- [Towards Full Delegation: Designing Ideal Agentic Behaviors for Travel Planning](https://mlsanity.com/paper/2411.13904/) (2024)
- [Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost](https://mlsanity.com/paper/2605.22502/) (2026)
- [In-Context Prompting Obsoletes Agent Orchestration for Procedural Tasks](https://mlsanity.com/paper/2604.27891/) (2026)
- [Procedural Knowledge Is Not Low-Rank: Why LoRA Fails to Internalize Multi-Step Procedures](https://mlsanity.com/paper/2607.21612/) (2026)
- [Leveraging Graph Structures and Large Language Models for End-to-End Synthetic Task-Oriented Dialogues](https://mlsanity.com/paper/2501.11977/) (2025)

## Abstract (arXiv)

This paper explores SynTOD, a new synthetic data generation approach for developing end-to-end Task-Oriented Dialogue (TOD) Systems capable of handling complex tasks such as intent classification, slot filling, conversational question-answering, and retrieval-augmented response generation, without relying on crowdsourcing or real-world data. SynTOD utilizes a state transition graph to define the desired behavior of a TOD system and generates diverse, structured conversations through random walks and response simulation using large language models (LLMs). In our experiments, using graph-guided response simulations leads to significant improvements in intent classification, slot filling and response relevance compared to naive single-prompt simulated conversations. We also investigate the end-to-end TOD effectiveness of different base and instruction-tuned LLMs, with and without the constructed synthetic conversations. Finally, we explore how various LLMs can evaluate responses in a TOD system and how well they are correlated with human judgments. Our findings pave the path towards quick development and evaluation of domain-specific TOD systems. We release our datasets, models, and code for research purposes.