{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/simulating-task-oriented-dialogues-with-state","title":"Simulating Task-Oriented Dialogues with State Transition Graphs and Large Language Models","arxiv_id":"2404.14772","date":"2024-04-23","proceeding":null,"authors":["Chris Samarinas","Pracha Promthaw","Atharva Nijasure","Hansi Zeng","Julian Killingback","Hamed Zamani"],"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, 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.","url_abs":"https://arxiv.org/abs/2404.14772v1","url_pdf":"https://arxiv.org/pdf/2404.14772v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"simulating-task-oriented-dialogues-with-state","repo_url":"https://github.com/algoprog/syntod","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"conversational-question-answering","task_name":"Conversational Question Answering"},{"task_slug":"dialogue-state-tracking","task_name":"Dialogue State Tracking"},{"task_slug":"intent-classification","task_name":"Intent Classification"},{"task_slug":"question-answering","task_name":"Question Answering"},{"task_slug":"response-generation","task_name":"Response Generation"},{"task_slug":"slot-filling","task_name":"Slot Filling"},{"task_slug":"synthetic-data-generation","task_name":"Synthetic Data Generation"},{"task_slug":"task-oriented-dialogue-systems","task_name":"Task-Oriented Dialogue Systems"},{"task_slug":"text-generation","task_name":"Text Generation"},{"task_slug":"intent-classification-1","task_name":"intent-classification"},{"task_slug":"slot-filling-1","task_name":"slot-filling"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.14772","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}