[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-638985-105":59,"doc-detail-638985-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","metamo-psychological-distortion-detection-for-cognition-aware-coaching","Metamo - Psychological Distortion Detection for Cognition-aware Coaching","","Metamo is a browser-based dialogue system that turns an off-the-shelf large language model into an empathetic coach for everyday workplace concerns. It uses a lightweight single-pass wrapper to identify cognitive distortions and emotions, then produces a question-centered reply that promotes reflection within one model call. The response time stays under two seconds in the API. A web interface visualizes detected emotions via an animated avatar and distortion badges, while a safety layer blocks medical advice and routes crisis language. Experiments on public corpora and a small company user study improve emotion-recognition quality, response diversity, empathy, and usability without increasing latency, and the system is model-agnostic.",{"@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/metamo-psychological-distortion-detection-for-cognition-aware-coaching/638985/",{"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/metamo-psychological-distortion-detection-for-cognition-aware-coaching/638985.png","ImageObject",300,407,{"name":92,"@type":93},"Marglet","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-29","2026-10-22",true,{"@type":102,"interactionType":103,"userInteractionCount":8},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is Metamo, and what does it do for workplace coaching?","Question",{"text":112,"@type":113},"Metamo is a browser-based dialogue system that transforms a standard large language model into an empathetic coach for everyday workplace concerns. It detects cognitive distortions and the user’s emotion, then generates question-centered replies to encourage reflection.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does Metamo keep latency low while improving coaching quality?",{"text":117,"@type":113},"Metamo uses a light, single-pass wrapper so all steps—distortion identification, emotion recognition, and reply generation—happen within one model call. This keeps response time below two seconds in the API while enriching feedback with cognitively grounded insight.",{"name":119,"@type":110,"acceptedAnswer":120},"What safety measures does Metamo include?",{"text":121,"@type":113},"A safety layer blocks medical advice and redirects crisis language to human hotlines. This ensures coaching responses handle sensitive cases appropriately.","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},638985,1792700986,{"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":8,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":129,"read_time":144},2336477982702,"https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc","Metamo: Empowering Large Language Models with Psychological Distortion Detection for Cognition-aware Coaching  \nHajime Hotta 1 , Huu-Loi Le2 , Manh-Cuong Phan3 , Minh-Tien Nguyen3 *  \n1 Hajime Institute, Kuala Lumpur, Malaysia.  \n[hotta@hajime.institute](hotta@hajime.institute)  \n[2](2 AI Academy Vietnam)[ AI Academy Vietnam](2 AI Academy Vietnam), [Vietnam](Vietnam).  \n[loilh@aiacademy.edu.vn](loilh@aiacademy.edu.vn)  \n3 Hung Yen University of Technology and Education, Hung Yen, Vietnam.  \n[cuongpm@spkt.edu.vn](cuongpm@spkt.edu.vn) ; [tiennm@utehy.edu.vn](tiennm@utehy.edu.vn)  \nAbstract  \nWe demonstrate Metamo, a browser-based dialogue system that transforms an off-the-shelf large language model into an empathetic coach for everyday workplace concerns. Metamo introduces a light, single-pass wrapper that ﬁrst identiﬁes the cognitive distortion behind an emotion, then recognizes the user's emotion, and ﬁnally produces a question-centered reply that invites reﬂection, all within one model call. The wrapper keeps the response time below two seconds in the API, yet enriches the feedback with cognitively grounded insight. A front-end web interface renders the detected emotion as an animated avatar and shows distortion badges in real time, whereas a safety layer blocks medical advice and redirects crisis language to human hotlines. Empirical testson public corpora conﬁrmed that the proposed design improved emotion-recognition quality and response diversity without sacriﬁcing latency. A small user study with company staff reported higher perceived empathy and usability than a latency-matched baseline. Metamois model-agnostic, illustrating a practical path toward cognition-aware coaching tools.  \n1 Introduction  \nConversational coaching tools have begun to accompany performance reviews, career planning, and daily self-reﬂection in the workplace (Mitchell et al., 2022 ; Beinema et al., 2023 ; Arakawa and Yakura, 2024 ; Ong et al., 2024) . Built on large language models (LLMs), such systems can deliver ﬂuent encouragement; however, they typically operate with a single prompt that folds perception and advice into one turn. It leads to two limitations. First, the generated guidance is often generic, without empathy, because the prompt lacks an explicit representation of why the user feels distressed. Second, multi-step prompting or tool calling pushes  \n* Corresponding Author.  \nresponse latency beyond the ﬁve-second window that humans perceive as natural.  \nPsychological research attributes many negative emotions to recurring thought patterns, known as cognitive distortions (Beck, 2020) . Recent NLP studies have shown that prompting LLMs to label such distortions can sharpen downstream reasoning (Chen et al., 2023 ; Wang et al., 2024 ; Lim et al., 2024), but existing pipelines are usually designed with two separate steps: emotion recognition with shallow textual representation, and response generation. This makes ill-suited for interactive and empathetic coaching (Liong and Patel, 2024) .  \nWe argue that conversational coaching systems should be empowered by a deeper understanding of human thinking that fosters empathetic effective communication between humans and AI models. To address this argument, this study presents Metamo, a demonstration system that is empowered by psychological distortion detection. The system uses a compact prompt to ﬁrst yield a ten-way distortion label, then emotion labels, and ﬁnally, a dialogue move that combines a Socratic follow-up question with a brief reframing suggestion. The design preserves latency while making cognitive analysis transparent: the web client maps the emotion to an avatar's facial expression and displays the distortion as a color-coded badge.  \nWe evaluated Metamo under zero-shot conditions on EMPATHETICDIALOGUES (Rashkin et al., 2019) and a subset of EDOS (Welivita et al., 2021) . The wrapper improves emotion recognition accuracy and response diversity over strong baselines, yet maintai","cbCaipa8lCKAK2QI","https://ap.wps.com/l/cbCaipa8lCKAK2QI","pdf",603142,11,"English","# Abstract\n# 1 Introduction\n# Chain of Emotion\n# Subjectivity assessment\n## Contrastive reasoning\n# Empathetic Response (ERG)","[{\"question\":\"What is Metamo, and what does it do for workplace coaching?\",\"answer\":\"Metamo is a browser-based dialogue system that transforms a standard large language model into an empathetic coach for everyday workplace concerns. It detects cognitive distortions and the user’s emotion, then generates question-centered replies to encourage reflection.\"},{\"question\":\"How does Metamo keep latency low while improving coaching quality?\",\"answer\":\"Metamo uses a light, single-pass wrapper so all steps—distortion identification, emotion recognition, and reply generation—happen within one model call. This keeps response time below two seconds in the API while enriching feedback with cognitively grounded insight.\"},{\"question\":\"What safety measures does Metamo include?\",\"answer\":\"A safety layer blocks medical advice and redirects crisis language to human hotlines. This ensures coaching responses handle sensitive cases appropriately.\"}]","Metamo - Psychological Distortion Detection for Cognition-aware Coaching | PDF",28]