[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-1-en-105":3,"doc-seo-275092-105":53,"doc-detail-275092-en":127},{"code":4,"msg":5,"data":6},0,"success",[7,14,19,24,29,34,39,44,49],{"id":8,"doc_module":9,"doc_module_name":10,"category_name":11,"show_sort_weight":12,"slug":13},11,1,"Template","Presentations",90,"presentations",{"id":15,"doc_module":9,"doc_module_name":10,"category_name":16,"show_sort_weight":17,"slug":18},12,"Resumes",80,"resumes",{"id":20,"doc_module":9,"doc_module_name":10,"category_name":21,"show_sort_weight":22,"slug":23},14,"Invoices",70,"invoices",{"id":25,"doc_module":9,"doc_module_name":10,"category_name":26,"show_sort_weight":27,"slug":28},15,"Posters",60,"posters",{"id":30,"doc_module":9,"doc_module_name":10,"category_name":31,"show_sort_weight":32,"slug":33},16,"Social Media",50,"social-media",{"id":35,"doc_module":9,"doc_module_name":10,"category_name":36,"show_sort_weight":37,"slug":38},17,"Forms",40,"forms",{"id":40,"doc_module":9,"doc_module_name":10,"category_name":41,"show_sort_weight":42,"slug":43},18,"Letters",30,"letters",{"id":45,"doc_module":9,"doc_module_name":10,"category_name":46,"show_sort_weight":47,"slug":48},21,"Paper Templates",5,"papers-templates",{"id":50,"doc_module":9,"doc_module_name":10,"category_name":51,"show_sort_weight":4,"slug":52},158,"General","general-158",{"code":4,"msg":54,"data":55},"ok",{"site_id":56,"language":57,"slug":58,"title":59,"keywords":60,"description":61,"schema_data":62,"social_meta":120,"head_meta":122,"extra_data":124,"updated_unix":126},105,"en","understanding-and-supporting-formal-email-exchange-by-answering-ai-generated-questions","Understanding and Supporting Formal Email Exchange by Answering AI-Generated Questions","","Replying to formal emails is time-consuming and cognitively demanding, since it requires crafting courteous phrasing and satisfying the sender’s expectations. Although systems powered by large language models aim to simplify reply generation, users often must provide detailed prompts to obtain appropriate drafts. An LLM-based question-and-answer workflow can instead guide users to respond through short, email-derived questions, improving drafting efficiency and reducing workload while preserving reply quality.",{"@graph":63,"@context":119},[64,80,102],{"@type":65,"itemListElement":66},"BreadcrumbList",[67,71,74,77],{"item":68,"name":69,"@type":70,"position":9},"https://docshare.wps.com","Home","ListItem",{"item":72,"name":10,"@type":70,"position":73},"https://docshare.wps.com/template/",2,{"item":75,"name":11,"@type":70,"position":76},"https://docshare.wps.com/template/presentations/",3,{"item":78,"name":59,"@type":70,"position":79},"https://docshare.wps.com/template/understanding-and-supporting-formal-email-exchange-by-answering-ai-generated-questions/275092/",4,{"url":78,"name":59,"@type":81,"image":82,"author":87,"headline":59,"publisher":90,"fileFormat":93,"inLanguage":57,"description":61,"dateModified":94,"datePublished":95,"encodingFormat":93,"isAccessibleForFree":96,"interactionStatistic":97},"DigitalDocument",{"url":83,"@type":84,"width":85,"height":86},"https://docshare.wps.com/thumbnails/understanding-and-supporting-formal-email-exchange-by-answering-ai-generated-questions/275092.png","ImageObject",442,249,{"name":88,"@type":89},"Sarah ","Person",{"url":68,"name":91,"@type":92},"DocShare","Organization","application/pdf","2026-10-28","2026-09-15",true,{"@type":98,"interactionType":99,"userInteractionCount":101},"InteractionCounter",{"@type":100},"ViewAction",9,{"@type":103,"mainEntity":104},"FAQPage",[105,111,115],{"name":106,"@type":107,"acceptedAnswer":108},"Why is replying to formal emails cognitively demanding?","Question",{"text":109,"@type":110},"It requires crafting polite wording and providing responses that match the sender’s requests. Tone, style, diction, and structure must be handled carefully.","Answer",{"name":112,"@type":107,"acceptedAnswer":113},"What limitation exists in prompt-based LLM email reply systems?",{"text":114,"@type":110},"Users must craft detailed prompts to achieve the desired content, tone, and style. If results are not satisfactory, prompts may need to be created repeatedly.",{"name":116,"@type":107,"acceptedAnswer":117},"How does the QA-based approach (ResQ) help users reply more efficiently?",{"text":118,"@type":110},"The system analyzes the incoming email and generates short AI-generated questions. Users answer these questions to obtain an AI draft, then check and revise before sending the reply.","https://schema.org",{"og:url":78,"og:type":121,"og:title":59,"og:site_name":91,"og:description":61},"article",{"robots":123,"canonical":78},"index,follow",{"doc_id":125,"site_id":56},275092,1791734437,{"code":4,"msg":5,"data":128},{"doc_id":125,"user_id":129,"nickname":88,"user_avatar":130,"doc_module":9,"category_id":8,"category_name":11,"doc_title":59,"doc_description":61,"doc_content":131,"file_id":132,"file_url":133,"file_type":134,"file_size":135,"view_count":101,"is_deleted":4,"is_public":9,"is_downloadable":9,"audit_status":9,"page_count":136,"language":137,"language_code":57,"site_id":56,"html_lang":57,"table_of_contents":138,"faqs":139,"seo_title":140,"seo_description":61,"update_tm":141,"read_time":142},962085320529,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","Understanding and Supporting Formal Email Exchange by Answering AI-Generated Questions  \nYusuke Miura  \n[miura.yusuke@toki.waseda.jp](miura.yusuke@toki.waseda.jp)[ ](miura.yusuke@toki.waseda.jp)Waseda University Tokyo, Japan  \nChi-Lan Yang  \n[chilan.yang@cyber.t.u-tokyo.ac.jp](chilan.yang@cyber.t.u-tokyo.ac.jp)[ ](chilan.yang@cyber.t.u-tokyo.ac.jp)The University of Tokyo Tokyo, Japan  \nMasaki Kuribayashi  \n[rugbykuribayashi@waseda.jp](rugbykuribayashi@waseda.jp)[ ](rugbykuribayashi@waseda.jp)Waseda University Tokyo, Japan  \narXiv :2502 .03804v2 [ cs .HC] 7 Feb 2025  \nKeigo Matsumoto  \n[matsumoto@cyber.t.u-tokyo.ac.jp](matsumoto@cyber.t.u-tokyo.ac.jp)[ ](matsumoto@cyber.t.u-tokyo.ac.jp)The University of Tokyo Tokyo, Japan  \nHideaki Kuzuoka  \n[kuzuoka@cyber.t.u-tokyo.ac.jp](kuzuoka@cyber.t.u-tokyo.ac.jp)[ ](kuzuoka@cyber.t.u-tokyo.ac.jp)The University of Tokyo Tokyo, Japan  \nShigeo Morishima  \n[shigeo@waseda.jp](shigeo@waseda.jp)  \nWaseda Research Institute for Science and Engineering Tokyo, Japan  \n2. Answer the Questions 3. Get Draft by AI 4. Check & Revise  \n1. Receive Email  \n5. Send Reply  \nFigure 1: In our system,(1) users receive an email,(2) communicate their intentions by answering AI-generated questions,(3) receive an AI-generated draft,(4) make any necessary revisions, and finally (5) send the reply. This process allows users to craft responses efficiently, reducing their overall workload.  \nAbstract  \nReplying to formal emails is time-consuming and cognitively demanding, as it requires crafting polite phrasing and providing an adequate response to the sender’s demands. Although systems with Large Language Models (LLMs) were designed to simplify the email replying process, users still need to provide detailed prompts to obtain the expected output. Therefore, we proposed and evaluated an LLM-powered question-and-answer (QA)-based approach for users to reply to emails by answering a set of simple and short questions generated from the incoming email. We developed a prototype system, ResQ, and conducted controlled and field experiments with 12 and 8 participants. Our results demonstrated that the QA-based approach improves the efficiency of replying to emails and reduces workload while maintaining email quality, compared to a conventional prompt-based approach that requires users to craft appropriate prompts to obtain email drafts. We discuss how the QA-based approach influences the email reply process and interpersonal relationship dynamics, as well as the opportunities and challenges associated with using a QA-based approach in AI-mediated communication.  \nThis work is licensed under a Creative Commons Attribution 4 .0 International License. CHI’25, Yokohama, Japan  \n© 2025 Copyright held by the owner/author(s) .  \nACM ISBN 979-8-4007-1394-1/25/04  \n[https://doi.org/10.1145/3706598.3714016](https://doi.org/10.1145/3706598.3714016)  \nCCS Concepts  \n• Human-centered computing → Empirical studies in collaborative and social computing.  \nKeywords  \nAI-Mediated Communication, Large Language Models, Email  \nACM Reference Format:  \nYusuke Miura, Chi-Lan Yang, Masaki Kuribayashi, Keigo Matsumoto, Hideaki Kuzuoka, and Shigeo Morishima. 2025. Understanding and Supporting Formal Email Exchange by Answering AI-Generated Questions. In CHI Conference on Human Factors in Computing Systems (CHI’25), April 26-May 1, 2025, Yokohama, Japan. ACM, New York, NY, USA, 20 pages. [https:](https:)//[doi.org/10.1145/3706598.3714016](doi.org/10.1145/3706598.3714016)  \n1 Introduction  \nEmail is a common tool for users to share information [59, 73] and manage tasks [7] . It has been found that users spend an average of 28% of their workweek reading and replying to emails [38] . However, for many, checking and responding to emails is timeconsuming and cognitively demanding [50] . Responding to emails, especially in cultures that value courteous email exchanges, requires users to understand the sender’s requests and compose polite messages that refle","cbCaipTTsFFKhB5O","https://ap.wps.com/l/cbCaipTTsFFKhB5O","pdf",1870725,20,"English","# Introduction\n## Problem: workload and cognitive demand\n## Prior AI-mediated approaches\n## Proposed QA-based approach","[{\"question\":\"Why is replying to formal emails cognitively demanding?\",\"answer\":\"It requires crafting polite wording and providing responses that match the sender’s requests. Tone, style, diction, and structure must be handled carefully.\"},{\"question\":\"What limitation exists in prompt-based LLM email reply systems?\",\"answer\":\"Users must craft detailed prompts to achieve the desired content, tone, and style. If results are not satisfactory, prompts may need to be created repeatedly.\"},{\"question\":\"How does the QA-based approach (ResQ) help users reply more efficiently?\",\"answer\":\"The system analyzes the incoming email and generates short AI-generated questions. Users answer these questions to obtain an AI draft, then check and revise before sending the reply.\"}]","Understanding and Supporting Formal Email Exchange by Answering AI-Generated Questions | PDF",1789484949,7]