[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-665601-105":59,"doc-detail-665601-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","graphologue-exploring-large-language-model-responses-with-interactive-diagrams","Graphologue - Exploring Large Language Model Responses with Interactive Diagrams","","Large language models (LLMs) have rapidly gained popularity for their accessibility and ability to synthesize text answers to diverse questions. Yet text-only interfaces like ChatGPT struggle with complex information tasks, producing verbose outputs and offering limited support for flexible, non-linear exploration. A formative study with ten participants shows that people have difficulty quickly comprehending and interacting with such information. Graphologue addresses this by converting streamed LLM text into interactive node-link diagrams.",{"@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":30,"@type":76,"position":81},"https://docshare.wps.com/document/technology/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/graphologue-exploring-large-language-model-responses-with-interactive-diagrams/665601/",{"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/graphologue-exploring-large-language-model-responses-with-interactive-diagrams/665601.png","ImageObject",300,407,{"name":92,"@type":93},"8796093062539","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-10-29",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 problem does Graphologue target in current LLM interfaces?","Question",{"text":112,"@type":113},"Text-based conversational interfaces can be overly verbose and poorly suited for complex information tasks. This makes it harder for users to quickly understand and flexibly explore information.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does Graphologue transform LLM responses for users?",{"text":117,"@type":113},"Graphologue converts streamed LLM text-based responses into graphical node-link diagrams in real time, extracting entities and relationships from the responses.",{"name":119,"@type":110,"acceptedAnswer":120},"What interactive capabilities does Graphologue provide?",{"text":121,"@type":113},"Users can interact with the diagrams to adjust the graphical presentation. The system also supports follow-up context-specific prompts to retrieve more information via diagram-driven, non-linear dialogue.","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},665601,1793305143,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":66,"doc_module":4,"category_id":29,"category_name":30,"doc_title":65,"doc_description":67,"doc_content":133,"file_id":134,"file_url":135,"file_type":136,"file_size":137,"view_count":8,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":46,"language":138,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":139,"faqs":140,"seo_title":141,"seo_description":67,"update_tm":129,"read_time":31},8796093062539,"Graphologue: Exploring Large Language Model Responses  \nwith Interactive Diagrams  \narXiv :2305 . 11473v2 [ cs .HC] 4 Aug 2023  \nPeiling Jiang∗ [peiling@ucsd.edu](peiling@ucsd.edu)[ ](peiling@ucsd.edu)University of California San Diego La Jolla, California, USA  \nSteven P. Dow  \n[spdow@ucsd.edu](spdow@ucsd.edu)[ ](spdow@ucsd.edu)University of California San Diego La Jolla, California, USA  \nJude Rayan∗ [jrayan@ucsd.edu](jrayan@ucsd.edu)[ ](jrayan@ucsd.edu)University of California San Diego La Jolla, California, USA  \nHaijun Xia  \n[haijunxia@ucsd.edu](haijunxia@ucsd.edu)[ ](haijunxia@ucsd.edu)University of California San Diego La Jolla, California, USA  \nFigure 1: Graphologue constructs an interactive diagram in real-time as GPT-4 text responses are streamed in.  \nABSTRACT  \nLarge language models (LLMs) have recently soared in popularity due to their ease of access and the unprecedented ability to synthesize text responses to diverse user questions. However, LLMs like ChatGPT present significant limitations in supporting complex information tasks due to the insufficient affordances of the text-based medium and linear conversational structure. Through a formative study with ten participants, we found that LLM interfaces often present long-winded responses, making it difficult for people to quickly comprehend and interact flexibly with various pieces of information, particularly during more complex tasks. We present Graphologue, an interactive system that converts textbased responses from LLMs into graphical diagrams to facilitate information-seeking and question-answering tasks. Graphologue employs novel prompting strategies and interface designs to extract entities and relationships from LLM responses and constructs node-link diagrams in real-time. Further, users can interact with the diagrams to flexibly adjust the graphical presentation and to  \n∗ Both authors contributed equally to this research.  \nPermission to make digital or hard copies of part or all ofthis work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for third-party components of this work must be honored. For all other uses, contact the owner/author(s) .  \nUIST ’23, October 29-November 1, 2023, San Francisco, CA, USA © 2023 Copyright held by the owner/author(s) .  \nACM ISBN 979-8-4007-0132-0/23/10 .  \n[https://doi.org/10.1145/3586183.3606737](https://doi.org/10.1145/3586183.3606737)  \nsubmit context-specific prompts to obtain more information. Utilizing diagrams, Graphologue enables graphical, non-linear dialogues between humans and LLMs, facilitating information exploration, organization, and comprehension.  \nCCS CONCEPTS  \n• Information systems → Users and interactive retrieval; • Human-centered computing → Human computer interaction (HCI); Visualization.  \nKEYWORDS  \nLarge Language Model, Natural Language Interface, Visualization  \nACM Reference Format:  \nPeiling Jiang, Jude Rayan, Steven P. Dow, and Haijun Xia. 2023. Graphologue: Exploring Large Language Model Responses with Interactive Diagrams. In The 36th Annual ACM Symposium on User Interface Software and Technology (UIST ’23), October 29-November 1, 2023, San Francisco, CA, USA. ACM, New York, NY, USA, 20 pages. [https://doi.org/10.1145/3586183.3606737](https://doi.org/10.1145/3586183.3606737)  \n1 INTRODUCTION  \nLarge Language Models (LLMs) have seen a surge in popularity due to their impressive ability to generate high-quality textual responses to natural language prompts across a wide variety of tasks [14] . More than a billion people have used interfaces to LLMs, such as ChatGPT, to obtain information and answers to questions. With the  \npotential to dramatically transform how people complete information processing tasks, LLMs are becoming increasingly important tools in various fields [14, 64] .  \nDespite their potential, inter","cbCaidmKRxUFeo5X","https://ap.wps.com/l/cbCaidmKRxUFeo5X","pdf",3377508,"English","# Abstract\n# Introduction\n## Limitations of text-based LLM interfaces\n## Benefits of graphical representations\n## Goal of the project","[{\"question\":\"What problem does Graphologue target in current LLM interfaces?\",\"answer\":\"Text-based conversational interfaces can be overly verbose and poorly suited for complex information tasks. This makes it harder for users to quickly understand and flexibly explore information.\"},{\"question\":\"How does Graphologue transform LLM responses for users?\",\"answer\":\"Graphologue converts streamed LLM text-based responses into graphical node-link diagrams in real time, extracting entities and relationships from the responses.\"},{\"question\":\"What interactive capabilities does Graphologue provide?\",\"answer\":\"Users can interact with the diagrams to adjust the graphical presentation. The system also supports follow-up context-specific prompts to retrieve more information via diagram-driven, non-linear dialogue.\"}]","Graphologue - Exploring Large Language Model Responses with Interactive Diagrams | PDF"]