[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-657806-105":59,"doc-detail-657806-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","evaluating-compliance-with-visualization-guidelines-in-diagrams-for-scientific-publications-using-large-vision-language-models","Evaluating Compliance with Visualization Guidelines in Diagrams for Scientific Publications Using Large Vision Language Models","","Diagrams widely communicate data in scientific publications, yet visualization guidelines are often unknown or not followed, causing misinformation through inaccurate or incomplete diagram elements. This study applies large Vision Language Models to analyze scientific diagrams and detect potential violations of selected visualization principles. Five open-source VLMs and five prompting strategies are evaluated with guideline-derived question sets, showing strong performance on diagram types, 3D effects, axes labels, lines, colors, and legends, while feedback on image quality and tick marks/labels is less reliable.",{"@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/evaluating-compliance-with-visualization-guidelines-in-diagrams-for-scientific-publications-using-large-vision-language-models/657806/",{"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/evaluating-compliance-with-visualization-guidelines-in-diagrams-for-scientific-publications-using-large-vision-language-models/657806.png","ImageObject",300,407,{"name":92,"@type":93},"cryingin4k","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-30","2026-10-26",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What problem does the paper address about diagrams in scientific publications?","Question",{"text":112,"@type":113},"It addresses that visualization guidelines are often not known or followed, which can lead to misinformation from inaccurate or incomplete diagram information.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How are Vision Language Models used in this work?",{"text":117,"@type":113},"The study uses large VLMs to analyze diagrams and identify potential issues relative to selected visualization principles and guidelines.",{"name":119,"@type":110,"acceptedAnswer":120},"Which aspects do the VLMs perform best and worst on?",{"text":121,"@type":113},"They work well for diagram types, 3D effects, axes labels, lines, colors, and legends, but cannot reliably provide feedback about image quality and tick marks/labels.","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},657806,1792990575,{"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":24,"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},137458181193,"https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8","arXiv :2506 . 19825v 1 [ cs .AI] 24 Jun 2025  \nEvaluating Compliance with Visualization Guidelines in Diagrams for Scientific Publications Using Large Vision Language Models  \nJohannes Rückert 1⋆[0000−0002−5038−5899](B) , Louise Bloch 1 ,2 ,3⋆[0000−0001−7540−4980], and Christoph M.  \nFriedrich 1 ,2[0000−0002−3315−7536]  \n1 Department of Computer Science, University of Applied Sciences and Arts  \nDortmund, Emil-Figge-Str. 42, 44227 Dortmund, Germany {johannes.rueckert,louise.bloch,[christoph.friedrich}@fh-dortmund.de](christoph.friedrich}@fh-dortmund.de)  \n2 Institute for Medical Informatics, Biometry and Epidemiology (IMIBE), 45147 Essen, Germany  \n3 Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen, 45147 Essen, Germany  \nAbstract. Diagrams are widely used to visualize data in publications.  \nThe research field of data visualization deals with defining principles and guidelines for the creation and use of these diagrams, which are often not known or adhered to by researchers, leading to misinformation caused by providing inaccurate or incomplete information.  \nIn this work, large Vision Language Models (VLMs) are used to analyze diagrams in order to identify potential problems in regards to selected data visualization principles and guidelines. To determine the suitability of VLMs for these tasks, five open source VLMs and five prompting strategies are compared using a set of questions derived from selected data visualization guidelines.  \nThe results show that the employed VLMs work well to accurately analyze diagram types (F1-score 82.49 %), 3D effects (F1-score 98.55 %), axes labels (F1-score 76.74 %), lines (RMSE 1.16), colors (RMSE 1.60) and legends (F1-score 96.64 %, RMSE 0.70), while they cannot reliably provide feedback about the image quality (F1-score 0.74 %) and tick marks/labels (F1-score 46.13 %) . Among the employed VLMs, Qwen2.5VL performs best, and the summarizing prompting strategy performs best for most of the experimental questions.  \nIt is shown that VLMs can be used to automatically identify a number of potential issues in diagrams, such as missing axes labels, missing legends, and unnecessary 3D effects. The approach laid out in this work can be extended for further aspects of data visualization.  \nKeywords: Document Analysis Systems · Chart Understanding · Visualization Guidelines · Vision Language Models.  \n⋆ these authors contributed equally to the work  \n2 J. Rückert et al.  \n1 Introduction  \nDiagrams can help researchers communicate their results more effectively. Previous research [34] found that the use of figures increases the citation counts of scientific publications across disciplines. This suggests that figures make information easier to understand and more convincing. Data visualization is afield of research focusing on how to represent data for clear, effective communication. However, previous research [26] found that many practitioners are not aware of these principles and guidelines. Additionally, there are many pitfalls in data visualization which may lead to misinformation caused by providing inaccurate or incomplete information [4,24] . Visualization guidelines [15,35] have been developed, providing detailed explanations of how to best present data. These detailed explanations are suitable for experts in data visualization. However, diagrams are created by an interdisciplinary community, making it complicated and time-consuming to understand and follow detailed guidelines. More recent publications provide tools such as checklists [15] or visualization linters [23] to make such guidelines accessible to a wider audience. Another approach is to develop tools that assess a diagram’s quality and provide feedback that can be useful for both diagram creators and readers. In [32], a diagram evaluation system based on classical image and text processing was evaluated. The resulting quality score includes the spatial proximity between the figure and the text ref","cbCailxkqBiOhcJq","https://ap.wps.com/l/cbCailxkqBiOhcJq","pdf",559447,"English","# Abstract\n# 1 Introduction\n## Prior work on figures and visualization principles\n## Diagram evaluation systems and quality scoring\n## LLM and VLM approaches for diagram advice","[{\"question\":\"What problem does the paper address about diagrams in scientific publications?\",\"answer\":\"It addresses that visualization guidelines are often not known or followed, which can lead to misinformation from inaccurate or incomplete diagram information.\"},{\"question\":\"How are Vision Language Models used in this work?\",\"answer\":\"The study uses large VLMs to analyze diagrams and identify potential issues relative to selected visualization principles and guidelines.\"},{\"question\":\"Which aspects do the VLMs perform best and worst on?\",\"answer\":\"They work well for diagram types, 3D effects, axes labels, lines, colors, and legends, but cannot reliably provide feedback about image quality and tick marks/labels.\"}]","Evaluating Compliance with Visualization Guidelines in Diagrams for Scientific Publications Using Large Vision Language Models | PDF",48]