CLApr 23, 2024

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

arXiv:2404.14772v14 citationsh-index: 6
Originality Incremental advance
AI Analysis

This work addresses the challenge of quickly developing domain-specific TOD systems without crowdsourcing, offering a practical solution for researchers and developers in dialogue systems.

The paper tackles the problem of developing end-to-end Task-Oriented Dialogue (TOD) systems for complex tasks like intent classification and slot filling by introducing SynTOD, a synthetic data generation approach that uses state transition graphs and large language models to create structured conversations without real-world data, resulting in significant improvements in intent classification, slot filling, and response relevance compared to naive methods.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes