[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-525942-105":59,"doc-detail-525942-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","beyond-accuracy-the-role-of-mental-models-in-human-ai-team-performance","Beyond Accuracy - The Role of Mental Models in Human-AI Team Performance","","Decisions made by human-AI teams are increasingly common in high-stakes domains such as healthcare, criminal justice, and finance. Strong team performance depends on more than AI accuracy: humans must understand how and when the AI can be relied on. The work studies humans’ mental models of AI error boundaries—when the AI errs—highlighting parsimony and stochasticity properties and a task dimensionality effect. Experiments link these factors to mental model formation and resulting team performance, and propose evaluation goals beyond accuracy for model selection and optimization.",{"@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/beyond-accuracy-the-role-of-mental-models-in-human-ai-team-performance/525942/",{"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/beyond-accuracy-the-role-of-mental-models-in-human-ai-team-performance/525942.png","ImageObject",300,407,{"name":92,"@type":93},"Oliver","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-16","2026-10-08",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What does the paper mean by an AI system’s error boundary?","Question",{"text":112,"@type":113},"It refers to the regions where the AI system is correct versus incorrect for a given input. Knowing this helps the human predict when the AI will err.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Which properties of the error boundary does the paper focus on?",{"text":117,"@type":113},"The paper highlights two key properties of the AI’s error boundary: parsimony and stochasticity, and also studies how a property of the task and its dimensionality influences mental models.",{"name":119,"@type":110,"acceptedAnswer":120},"How do mismatched mental models affect human-AI team performance?",{"text":121,"@type":113},"A mismatch can cause suboptimal decisions, such as trusting the AI when it is wrong or not trusting it when it is correct, which can reduce productivity and/or accuracy.","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},525942,1791591174,{"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":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":52,"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":143,"read_time":144,"preview_page_count":19,"preview_urls":145},8796095461610,"https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c","The Seventh AAAI Conference on Human  \nComputation and Crowdsourcing (HCOMP-19)  \nBeyond Accuracy: The Role of Mental Models in Human-AI Team Performance  \nGagan Bansal, Besmira Nushi,† Ece Kamar,† Walter S. Lasecki,‡ Daniel S. Weld, Eric Horvitz†  \nUniversity of Washington, Seattle,†Microsoft Research, Redmond,‡University of Michigan, Ann Arbor  \nAbstract  \nDecisions made by human-AI teams (e.g., AI-advised humans) are increasingly common in high-stakes domains such as healthcare, criminal justice, and ﬁnance. Achieving high team performance depends on more than just the accuracy of the AI system: Since the human and the AI may have different expertise, the highest team performance is often reached when they both know how and when to complement one another. We focus on a factor that is crucial to supporting such complementary: the human’s mental model of the AI capabilities, speciﬁcally the AI system’s error boundary (i.e. knowing “When does the AI err?”) . Awareness of this lets the human decide when to accept or override the AI’s recommendation. We highlight two key properties of an AI’s error boundary, parsimony and stochasticity, and a property of the task, dimensionality. We show experimentally how these properties affect humans’ mental models of AI capabilities and the resulting team performance. We connect our evaluations to related work and propose goals, beyond accuracy, that merit consideration during model selection and optimization to improve overall human-AI team performance.  \n1 Introduction  \nWhile many AI applications address automation, numerous others aim to team with people to improve joint performance or accomplish tasks that neither the AI nor people can solve alone (Gillies et al. 2016; Kamar 2016; Chakraborti and Kambhampati 2018; Lundberg et al. 2018; Lundgard et al. 2018) . In fact, many real-world, high-stakes applications deploy AI inferences to help human experts make better decisions, e.g., with respect to medical diagnoses, recidivism prediction, and credit assessment. Recommendations from AI systems—even if imperfect—can result in human-AI teams that perform better than either the human or the AI system alone (Wang et al. 2016; Jaderberg et al. 2019) .  \nSuccessfully creating human-AI teams puts additional demands on AI capabilities beyond task-level accuracy (Grosz 1996) . Speciﬁcally, even though team performance depends on individual human and AI performance, the team performance will not exceed individual performance levels if hu-  \nCopyright 􀀂c 2019, Association for the Advancement of Artiﬁcial Intelligence ([www.aaai.org](www.aaai.org)). All rights reserved.  \nFigure 1: AI-advised human decision making for readmission prediction: The doctor makes ﬁnal decisions using the classiﬁer’s recommendations. Check marks denote cases where the AI system renders a correct prediction, and crosses denote instances where the AI inference is erroneous. The solid line represents the AI error boundary, while the dashed line shows a potential human mental model of the error boundary.  \nman and the AI cannot account for each other’s strengthsand weaknesses. In fact, recent research shows that AI accuracy does not always translate to end-to-end team performance (Yin, Vaughan, and Wallach 2019; Lai and Tan 2018) . Despite this, and even for applications where people are involved, most AI techniques continue to optimize solely for accuracy of inferences and ignore team performance.  \nWhile many factors inﬂuence team performance, we study one critical factor in this work: humans’ mental model of the AI system that they are working with. In settings where the human is tasked with deciding when and how to make use of the AI system’s recommendation, extracting beneﬁts from the collaboration requires the human to build insights (i.e., a mental model) about multiple aspects of the capabilities of AI systems. A fundamental attribute is recognition of whether the AI system will succeed or fail for a particular input or","cbCaiiQ7D9LMrTE5","https://ap.wps.com/l/cbCaiiQ7D9LMrTE5","pdf",1365002,"English","# Introduction\n## Human-AI teaming in high-stakes domains\n## Mental models of AI capabilities and error boundaries\n## AI-advised human decision making setup","[{\"question\":\"What does the paper mean by an AI system’s error boundary?\",\"answer\":\"It refers to the regions where the AI system is correct versus incorrect for a given input. Knowing this helps the human predict when the AI will err.\"},{\"question\":\"Which properties of the error boundary does the paper focus on?\",\"answer\":\"The paper highlights two key properties of the AI’s error boundary: parsimony and stochasticity, and also studies how a property of the task and its dimensionality influences mental models.\"},{\"question\":\"How do mismatched mental models affect human-AI team performance?\",\"answer\":\"A mismatch can cause suboptimal decisions, such as trusting the AI when it is wrong or not trusting it when it is correct, which can reduce productivity and/or accuracy.\"}]","Beyond Accuracy - The Role of Mental Models in Human-AI Team Performance | PDF",1791493996,25,[146,150,154,158],{"page_no":8,"url":147,"width":148,"height":149},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/0aac07baae97ca1699971e0efefa1e9d.webp",983,1272,{"page_no":14,"url":151,"width":152,"height":153},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/4f1037ad966f1fdb0b63858599651799.webp",982,1270,{"page_no":81,"url":155,"width":156,"height":157},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/358a74f305f37c13b2d39aa4df1bbe6e.webp",981,1269,{"page_no":19,"url":159,"width":160,"height":161},"https://res-academy.cache.wpscdn.com/upload/kdocshare/2026-11-17/c6aed7890360ed87bb188d4f0f4ec8e3.webp",980,1268]