[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82150-en":3,"doc-seo-82150-105":29,"detail-sidebar-cat-0-en-105":90},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},82150,1099514067438,"River Wang","https://ap-avatar.wpscdn.com/avatar/100002539ee87300030?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780474512215547542",8,"Research & Report","Central Tendency Bias in Human Selection of AI Generated Design Variations","Image-generation AI systems increasingly support creative work by producing multiple design variations for users to evaluate and select. In human–AI co-creation workflows, selection becomes a decisive stage in which human judgment channels AI-generated possibilities into final outcomes. Although presenting many alternatives is meant to promote exploration, simultaneous multi-option presentation can introduce systematic decision biases. Using ensemble perception theory, this study tests how set variance shapes central tendency bias in aesthetic preference and representativeness tasks, finding higher variance drives center-proximal choices.","Central Tendency Bias in Human Selection of AI-Generated Design Variations  \n1st Huiyang Chen University of Michigan Ann Arbor, MI, USA [huiyangc@umich.edu](huiyangc@umich.edu)  \n2nd Keqing Jiao Carnegie Mellon University Pittsburgh, PA, USA [kjiao@andrew.cmu.edu](kjiao@andrew.cmu.edu)  \narXiv :2607 .09018v1 [ cs .HC] 10 Jul 2026  \nAbstract—Image-generation AI systems increasingly support creative work by producing multiple design variations for users to evaluate and select. In such human–AI co-creation workflows, selection becomes a critical stage where human judgment guides AI-generated possibilities toward final outcomes. While presenting multiple alternatives is intended to encourage exploration, the simultaneous multi-option presentation may introduce systematic biases in human decision making. Drawing on ensemble perception theory, we investigate whether these interfaces induce central tendency bias—the tendency to favor options closer to the center of a design set. We conducted a controlled experiment manipulating the variance of design sets (high vs. low) and measured participants’ selections in both aesthetic preference and representativeness tasks. Results show that higher variance increases the selection of center-proximal designs across both tasks. These findings suggest that multi-variation interfaces in image-generation AI systems may constrain selection diversity, revealing a potential tension between diversity in generated outputs and diversity in human selection outcomes.  \nIndex Terms—Image-generation AI, Human–AI collaboration, Ensemble perception, Design selection, Central tendency bias  \nI. INTRODUCTION  \nAI image-generation tools are increasingly embedded in creative workflows as collaborative partners [10], [11] . Contemporary tools such as Midjourney, DALL·E and Stable Diffusion often present users with multiple generated outputs that can be compared and selected. This interaction structure positions selection as a critical human-in-the-loop stage that determines which ideas progress and which are discarded.  \nDespite the growing emphasis on co-creation and collaborative intelligence, most research has focused on improving generation capabilities, enhancing ideation, and integrating AI into design workflows [8]–[12] . Comparatively less attention has been given to understanding the cognitive processes that shape how humans evaluate and select among generated alternatives. In many generative AI interfaces, outputs are displayed simultaneously in grid-based layouts containing multiple options. While this structure is intended to facilitate comparison and exploration, it may also impact how users internally represent and evaluate alternatives. We draw on ensemble perception theory—the finding that observers can automatically extract summary statistics from groups of simultaneously viewed objects, which can bias judgments toward the set’s central tendency [1]–[3], [5], [6] .  \nWe propose that generative AI selection contexts may inadvertently trigger similar ensemble mechanisms. When users evaluate multiple AI-generated designs simultaneously, they may form an implicit “mean representation” of the set [1], [2] . If this summary representation influences evaluation, humanselection in AI workflows may systematically gravitate toward center-proximal options, even when users aim to choose based on personal preference, innovation potential, or creativity. If higher generation diversity strengthens ensemble effects and reduces selection diversity, generative AI systems may paradoxically produce conservative outcomes despite offering diverse alternatives.  \nUnderstanding this structural interaction between interface design and human cognition is important for building user experiences that expand creative exploration. This study extends prior ensemble perception research to generative AI design contexts by investigating how variance within sets of AI-generated design variations influences human selection.  \nII. RE","cbCaiuQiSYQ0xikg","https://ap.wps.com/l/cbCaiuQiSYQ0xikg","pdf",2813493,1,5,"English","en",105,"# Introduction\n# Related Work\n## Ensemble Perception and Central Tendency Bias\n## Human-AI Collaboration in Generative Design","[{\"question\":\"What problem does the document address in AI design workflows?\",\"answer\":\"It addresses how presenting multiple AI-generated design variations simultaneously may bias human selection and reduce diversity in final choices.\"},{\"question\":\"What theory explains the potential bias discussed?\",\"answer\":\"The study draws on ensemble perception theory, which suggests observers can extract summary statistics from groups and may therefore favor the set’s central tendency.\"},{\"question\":\"How was the effect of design-set variance tested?\",\"answer\":\"A controlled experiment manipulated variance in design sets (high vs. low) and measured participants’ selections in aesthetic preference and representativeness tasks.\"}]",1784178452,13,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"central-tendency-bias-in-human-selection-of-ai-generated-design-variations","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/central-tendency-bias-in-human-selection-of-ai-generated-design-variations/82150/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does the document address in AI design workflows?","Question",{"text":74,"@type":75},"It addresses how presenting multiple AI-generated design variations simultaneously may bias human selection and reduce diversity in final choices.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What theory explains the potential bias discussed?",{"text":79,"@type":75},"The study draws on ensemble perception theory, which suggests observers can extract summary statistics from groups and may therefore favor the set’s central tendency.",{"name":81,"@type":72,"acceptedAnswer":82},"How was the effect of design-set variance tested?",{"text":83,"@type":75},"A controlled experiment manipulated variance in design sets (high vs. low) and measured participants’ selections in aesthetic preference and representativeness tasks.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,108,113,118,121,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":105,"show_sort_weight":106,"slug":107},"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":45,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":124,"slug":125},9,"Religion & Spirituality",20,"religion-spirituality",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":124,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":21,"slug":136},19,"General","general"]