[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-273648-105":59,"doc-detail-273648-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","generating-diverse-personas-for-user-simulators-to-test-interview-dialogue-systems","Generating Diverse Personas for User Simulators to Test Interview Dialogue Systems","","This paper addresses the high labor and cost of testing interview dialogue systems. Although such systems are valuable for gathering information from many users, manual testing demands substantial effort, especially when diverse user behaviors and topic-aligned personas are required. Prior user simulators focus largely on task-oriented dialogue, leaving personas insufficiently modeled for interviews. The proposed approach automatically generates diverse personas with a large language model and uses personality traits tied to communication styles to expand variation in simulated utterances.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/generating-diverse-personas-for-user-simulators-to-test-interview-dialogue-systems/273648/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/generating-diverse-personas-for-user-simulators-to-test-interview-dialogue-systems/273648.png","ImageObject",300,407,{"name":92,"@type":93},"Riley","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-17","2026-09-15",true,{"@type":102,"interactionType":103,"userInteractionCount":44},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why does testing interview dialogue systems require significant effort?","Question",{"text":112,"@type":113},"Testing requires simulating a wide range of user behaviors and personas. Creating many topic-aligned personas manually is especially labor-intensive, which drives high cost.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the proposed method generate personas for user simulators?",{"text":117,"@type":113},"The method provides a few manually created personas as examples and uses a large language model to automatically generate many additional personas.",{"name":119,"@type":110,"acceptedAnswer":120},"What helps increase the diversity of communication styles in the simulator?",{"text":121,"@type":113},"During persona generation, personality traits related to communication styles are specified, which increases variation in the resulting simulated utterances.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},273648,1789472373,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":44,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":56,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":143,"preview_page_count":4},1374391975076,"https://ap-avatar.wpscdn.com/avatar/14000253ca4ec9f6853?x-image-process=image/resize,m_fixed,w_180,h_180&k=1783305029341752051","Generating Diverse Personas for User Simulators to Test Interview  \nDialogue Systems  \nMikio Nakano1,2 , Kazunori Komatani2 , Hironori Takeuchi3  \n1 C4A Research Institute, Inc., Setagaya, Tokyo, Japan  \n2 SANKEN, University of Osaka, Ibaraki, Osaka, Japan  \n3Musashi University, Nerima, Tokyo, Japan  \n[mikio.nakano@c4a.jp](mikio.nakano@c4a.jp) , [komatani@sanken.osaka-u.ac.jp](komatani@sanken.osaka-u.ac.jp)  \n[h.takeuchi@cc.musashi.ac.jp](h.takeuchi@cc.musashi.ac.jp)  \narXiv : 2608 . 19549v 1 [cs .CL] 20 Aug 2026  \nAbstract  \nThis paper addresses the issue of the significant labor required to test interview dialogue systems. While interview dialogue systems are expected to be useful in various scenarios, like other dialogue systems, testing them with human users requires significant effort and cost. Therefore, testing with user simulators can be beneficial. Since most conventional user simulators have been primarily designed for training task-oriented dialogue systems, little attention has been paid to the personas of the simulated users. During development, testing interview dialogue systems requires simulating a wide range of user behaviors, but manually creating a large number of personas is labor-intensive. We propose a method that automatically generates personas for user simulators using a large language model. Furthermore, by assigning personality traits related to communication styles when generating personas, we aim to increase the diversity of communication styles in the user simulator. Experimental results show that the proposed method enables the user simulator to generate utterances with greater variation.  \n1 Introduction  \nInterview dialogue systems, which can efficiently gather information from many users, are a promising application of dialogue system technology and have attracted increasing research interest in recent years (Lang and Eskenazi, 2025 ; Hashimoto et al., 2025 ; Zeng et al., 2023) . However, building dialogue systems, including interview dialogue systems, incurs significant costs. One major cost is the effort required for testing. The goal of our study is to alleviate the manual effort for testing interview dialogue systems.  \nTo reduce testing costs, user simulation can be used instead of manual testing. However, existing user simulators have primarily been developed for the training and evaluation of task-oriented dialogue systems. Thus, we aim to develop a simu-  \nlator that is useful for testing interview dialogue systems.  \nWhen testing interview dialogue systems, simulating a wide variety of users is crucial. To increase variation, it is beneficial to have a large number of user personas (Zhang et al., 2018 ; Jiang et al., 2024 ; Hong et al., 2025) . However, manually creating numerous personas is labor-intensive. While using a large set of pre-constructed personas has been considered (Mazaré et al., 2018), this approach is unsuitable for interview dialogues, where personas need to be aligned with the specific interview topics.  \nTherefore, this paper proposes a method to generate diverse personas using large language models (LLMs) . In this method, a few manually created personas are provided as examples, and the LLMis tasked with generating a large number of additional personas. To ensure diversity in speaking styles and attitudes toward the system, personality traits are specified during generation.  \nEvaluation experiments demonstrated that the proposed method enables the creation of diverse dialogues through the generation of many personas. This increases the likelihood of discovering system issues. Note that detecting system issues from simulated dialogues is beyond the scope of our study. Manual inspection is one possible approach, but automated methods using LLMs are also conceivable (Finch et al., 2023) .  \nThe contributions of our study are as follows:  \n• We discuss that diverse personas are necessary for user simulators used in testing interview dialogue systems.  \n• We propose ","cbCaiegLa2uAi62b","https://ap.wps.com/l/cbCaiegLa2uAi62b","pdf",234187,"English","# Abstract\n# 1 Introduction\n## Interview dialogue systems\n## User simulation and persona diversity\n# 2 Related Work\n## 2.1 Interview Dialogue Systems\n## 2.2 Testing Dialogue Systems","[{\"question\":\"Why does testing interview dialogue systems require significant effort?\",\"answer\":\"Testing requires simulating a wide range of user behaviors and personas. Creating many topic-aligned personas manually is especially labor-intensive, which drives high cost.\"},{\"question\":\"How does the proposed method generate personas for user simulators?\",\"answer\":\"The method provides a few manually created personas as examples and uses a large language model to automatically generate many additional personas.\"},{\"question\":\"What helps increase the diversity of communication styles in the simulator?\",\"answer\":\"During persona generation, personality traits related to communication styles are specified, which increases variation in the resulting simulated utterances.\"}]","Generating Diverse Personas for User Simulators to Test Interview Dialogue Systems | PDF",48]