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

arXiv:2404.14772v1 Announce Type: new
Abstract: 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, …

abstract arxiv classification conversational crowdsourcing cs.cl data dialogue graphs language language models large language large language models paper question retrieval retrieval-augmented state synthetic synthetic data systems tasks transition type world