{"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/in-context-learning-user-simulators-for-task","title":"In-Context Learning User Simulators for Task-Oriented Dialog Systems","arxiv_id":"2306.00774","date":"2023-06-01","proceeding":null,"authors":["Silvia Terragni","Modestas Filipavicius","Nghia Khau","Bruna Guedes","André Manso","Roland Mathis"],"abstract":"This paper presents a novel application of large language models in user simulation for task-oriented dialog systems, specifically focusing on an in-context learning approach. By harnessing the power of these models, the proposed approach generates diverse utterances based on user goals and limited dialog examples. Unlike traditional simulators, this method eliminates the need for labor-intensive rule definition or extensive annotated data, making it more efficient and accessible. Additionally, an error analysis of the interaction between the user simulator and dialog system uncovers common mistakes, providing valuable insights into areas that require improvement. Our implementation is available at https://github.com/telepathylabsai/prompt-based-user-simulator.","url_abs":"https://arxiv.org/abs/2306.00774v1","url_pdf":"https://arxiv.org/pdf/2306.00774v1.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":"in-context-learning-user-simulators-for-task","repo_url":"https://github.com/telepathylabsai/prompt-based-user-simulator","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"in-context-learning-user-simulators-for-task","repo_url":"https://github.com/silviatti/prompt-based-user-simulator","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"goal-oriented-dialogue-systems","task_name":"Goal-Oriented Dialogue Systems"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"interactive-evaluation-of-dialog","task_name":"Interactive Evaluation of Dialog"},{"task_slug":"task-oriented-dialogue-systems","task_name":"Task-Oriented Dialogue Systems"},{"task_slug":"user-simulation","task_name":"User Simulation"}],"methods":[{"method_slug":"flan-t5","method_name":"Flan-T5"},{"method_slug":"llama","method_name":"LLaMA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.00774","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}