[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-289926-105":59,"doc-detail-289926-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","defining-and-evaluating-visual-language-models-basic-spatial-abilities-a-perspective-from-psychometrics-289926","Defining and Evaluating Visual Language Models’ Basic Spatial Abilities: A Perspective from Psychometrics","","The theory of multiple intelligences frames cognitive capabilities as hierarchical. To advance spatial artificial intelligence, the work introduces a psychometric framework that defines five Basic Spatial Abilities in visual language models: spatial perception, spatial relation, spatial orientation, mental rotation, and spatial visualization. Benchmarking 13 mainstream VLMs across nine validated experiments shows large human gaps (24.95 vs. 68.38) and reveals independent abilities, with interventions like chain-of-thought and 5-shot training offering limited architectural gains.",{"@graph":69,"@context":123},[70,84,106],{"@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/defining-and-evaluating-visual-language-models-basic-spatial-abilities-a-perspective-from-psychometrics-289926/289926/",{"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/defining-and-evaluating-visual-language-models-basic-spatial-abilities-a-perspective-from-psychometrics-289926/289926.png","ImageObject",300,407,{"name":92,"@type":93},"Mali","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-02","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What five Basic Spatial Abilities (BSAs) does the paper define for VLMs?","Question",{"text":113,"@type":114},"The paper defines five BSAs: Spatial Perception, Spatial Relation, Spatial Orientation, Mental Rotation, and Spatial Visualization.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How do the benchmark results compare VLMs to human performance?",{"text":118,"@type":114},"Across nine psychometric experiments, the average scores show a substantial gap versus humans (24.95 vs. 68.38).",{"name":120,"@type":111,"acceptedAnswer":121},"What do the interventions and training settings reveal about improving spatial abilities?",{"text":122,"@type":114},"Interventions such as chain-of-thought and 5-shot training produce accuracy gains (0.100 and 0.259), but they highlight limits driven by architectural constraints, including weak geometry encoding and missing dynamic simulation.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},289926,1790438333,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":145,"read_time":146,"preview_page_count":4},2336475104362,"https://ap-avatar.wpscdn.com/avatar/22000c4c46a41b752dd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786595829695023868","Defining and Evaluating Visual Language Models’ Basic Spatial Abilities:  \nA Perspective from Psychometrics  \nWenrui Xu1* , Dalin Lyu1* , Weihang Wang1* , Jie Feng2 , Chen Gao3 , Yong Li2  \n1 School of Architecture, Tsinghua University  \n2Department of Electronic Engineering, Tsinghua University  \n3BNRist, Tsinghua University  \n{xwr23,lvdl24,[wang-wh22}@mails.tsinghua.edu.cn](wang-wh22}@mails.tsinghua.edu.cn)[ ](wang-wh22}@mails.tsinghua.edu.cn){fengjie,chgao96, [liyong07}@tsinghua.edu.cn](liyong07}@tsinghua.edu.cn)  \narXiv :2502 . 11859v2 [ cs .CV] 20 Feb 2025  \nAbstract  \nThe Theory of Multiple Intelligences underscores the hierarchical nature of cognitive capabilities. To advance Spatial Artificial Intelligence, we pioneer a psychometric framework defining five Basic Spatial Abilities (BSAs) in Visual Language Models (VLMs): Spatial Perception, Spatial Relation, Spatial Orientation, Mental Rotation, and Spatial Visualization. Benchmarking 13 mainstream VLMs through nine validated psychometric experiments reveals significant gaps versus humans (average score 24.95 vs. 68.38), with three key findings: 1) VLMs mirror human hierarchies (strongest in 2D orientation, weakest in 3D rotation) with independent BSAs (Pearson’s r\u003C0 .4); 2) Smaller models such as Qwen2-VL-7B surpass larger counterparts, with Qwen leading (30.82) and InternVL2 lagging (19.6);  \n3) Interventions like chain-of-thought (0.100 accuracy gain) and 5-shot training (0.259 improvement) show limits from architectural constraints. Identified barriers include weak geometry encoding and missing dynamic simulation. By linking psychometric BSAs to VLM capabilities, we provide a diagnostic toolkit for spatial intelligence evaluation, methodological foundations for embodied AI development, and a cognitive science-informed roadmap for achieving human-like spatial intelligence.  \n1 Introduction  \nVisual Language Models (VLMs) excel in a wide range of specific tasks (Hong et al., 2023) . However, achieving human-like spatial intelligence for embodied AI applications such as visual navigation and embodied Q&A remains a challenge (Duranteet al., 2024 ; Duan et al., 2022) . Recent studies reveal that even advanced models like GPT-4o fail basic 2D spatial reasoning tasks that humans solve effortlessly (Tang et al., 2024) .  \n*These authors contributed equally to this work.  \n1Image source: Vandenberg and Kuse (1978) .  \nFigure 1: BSA measuring framework for VLMs 1.  \nGardner’s Theory of Multiple Intelligences (Bornstein and Gardner, 1986), which is widely accepted across disciplines, posits that human intelligence is hierarchical, with general intelligence (g) supported by subordinate intelligences including spatial intelligence. Spatial intelligence itself is also structured hierarchically, including five Basic Spatial Abilities (BSAs): Spatial Perception, Spatial Relation, Spatial Orientation, Mental Rotation, and Spatial Visualization. These abilities are crucial for advanced intelligence and provide a structured framework for evaluation.  \nHowever, existing studies assessing the spatial abilities of VLMs lack a solid theoretical foundation and typically focus on isolated abilities without a comprehensive framework, making it challenging to compare results across different studies or uncover potential interconnections between these abilities. Furthermore, most research omits human performance benchmarks, leaving the gap between VLMs and human largely unexplored.  \nTo address these gaps, we propose a psychometric framework using standardized human spatial tests to systematically evaluate VLMs’ BSAs, thereby establishing benchmarks and pathways for enhancing spatial intelligence in AI systems.  \n2 Related works  \n2.1 Psychometric Studies on Human Spatial Intelligence  \nHuman spatial intelligence, defined as the ability to mentally model and manipulate spatial environments (Bornstein and Gardner, 1986), has been studied since Spearman first identified it as an independent doma","cbCaibnPQHDvDZNq","https://ap.wps.com/l/cbCaibnPQHDvDZNq","pdf",12204355,17,"English","# Abstract\n# Introduction\n# Related works\n## Psychometric Studies on Human Spatial Intelligence","[{\"question\":\"What five Basic Spatial Abilities (BSAs) does the paper define for VLMs?\",\"answer\":\"The paper defines five BSAs: Spatial Perception, Spatial Relation, Spatial Orientation, Mental Rotation, and Spatial Visualization.\"},{\"question\":\"How do the benchmark results compare VLMs to human performance?\",\"answer\":\"Across nine psychometric experiments, the average scores show a substantial gap versus humans (24.95 vs. 68.38).\"},{\"question\":\"What do the interventions and training settings reveal about improving spatial abilities?\",\"answer\":\"Interventions such as chain-of-thought and 5-shot training produce accuracy gains (0.100 and 0.259), but they highlight limits driven by architectural constraints, including weak geometry encoding and missing dynamic simulation.\"}]","Defining and Evaluating Visual Language Models’ Basic Spatial Abilities: A Perspective from Psychometrics | PDF",1789638541,43]