[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84998-en":3,"doc-seo-84998-105":30,"detail-sidebar-cat-0-en-105":91},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},84998,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Biased or Personalized: The Impact of Personal Information on AI-driven Development","Generative AI increasingly supports software engineering by creating code and applications from natural-language specifications, while personalization can adapt outputs using inferred user characteristics and interaction history. Personalization improves usability but may shape generated software around developer attributes rather than stated task requirements. The study investigates how inferred developer identity influences generated artifacts, focusing on interface design, template content, and code structure. Experiments on 800 AI-generated websites and an observational study with 20 participants show meaningful demographic-driven differences, highlighting a fairness risk in AI-assisted programming.","Biased or Personalized? The Impact of Personal Information on  \nAI-driven Development  \nErfan Entezami  \nUniversity of Massachusetts Amherst Amherst, MA, USA [eentezami@cs.umass.edu](eentezami@cs.umass.edu)  \nMadeline Endres  \nUniversity of Massachusetts Amherst Amherst, MA, USA[mendres@umass.edu](mendres@umass.edu)  \narXiv :2607 .07480v 1 [ cs . SE] 8 Jul 2026  \nAbstract  \nGenerative AI is increasingly permeating software engineering, enabling developers to generate functions, files, and even entire applications from natural language specifications. AI systems are also becoming more personalized, adapting outputs based on inferred user characteristics and interaction history. While personalization may improve the development experience, it raises concerns that generated software could be shaped by attributes of the developer rather than by task requirements alone. Prior work has shown that generative AI can produce biased software artifacts, but little is known about how developer identity can bias generated code. We characterize three dimensions through which inferred developer attributes can influence generated artifacts: interface design, template content, and code structure. First, through controlled experiments on 800 AI-generated websites, we find that age-and gender-related signals produce significant differences across all three dimensions. Second, we conduct an observational study and follow-up interviews with 20 participants who used AI to create a personal website to both examine how personalization impacts software artifacts in practice, and also to understand how programmers perceive the boundary between personalization and bias. Together, our results show that developer attributes can meaningfully influence generated software beyond stated requirements, highlighting a previously underexplored tension between personalization and fairness in AI-assisted programming.  \n1 Introduction  \nWhat happens when an AI coding assistant knows something about its user? Should the software generated for a 25-year-old woman differ in its implementation from that generated for a 65-year-old man, even when both request the same application? As large language models (LLMs) become more personalized through conversational history and inferred user characteristics [34], these questions are increasingly relevant. Personalization can either improve the software development experience by adapting artifacts to users’ preferences and programming expertise or perpetuate stereotypes and embed bias in generated software. AI-assisted tools have become an integral to many domains, from education [3] to healthcare [1] . Software engineering is no exception. Recent advances in LLMs have led to widespread adoption for tasks such as code generation [29], debugging [65], and documentation [5, 14, 69] . As these models improve, the technical expertise required to use them has decreased, enabling more users to develop software [18] . Users can increasingly transform natural language ideas directly into working software with little or no manual coding, a paradigm commonly known as vibe coding [57] .  \nSimultaneously, LLMs can produce biased outputs that reflect existing stereotypes across a wide array of domains [20, 25, 33, 49, 70] . LLMs can generate different output for different users, inferring user characteristics from information explicitly or implicitly included in the prompt [34, 51, 66], behavior amplified by the increasing use of cross-conversational memory [17] . For example, implicit racial indicators in a prompt can lead state-of-the-art chatbots to recommend different colleges or neighborhoods to otherwise identical users [34] .  \nThese concerns naturally extend to software development. Recent work has found that the behavior of generated code at runtime can vary in demographic-sensitive contexts, raising algorithmic fairness concerns [28, 38] . Demographic bias has also been observed in broader software contexts, including how programme","cbCaimgAxJec6iAX","https://ap.wps.com/l/cbCaimgAxJec6iAX","pdf",1494639,2,1,13,"English","en",105,"# Abstract\n# Introduction\n## Motivation and Problem Statement\n## Background on Personalization and Bias\n## Prior Work and Research Gap\n## Research Questions and Study Context\n## Experimental Design","[{\"question\":\"What problem does the paper investigate about personalized AI coding assistants?\",\"answer\":\"It investigates how inferred developer demographic characteristics can influence generated software artifacts beyond the stated requirements, potentially embedding bias into code and design outputs.\"},{\"question\":\"Which aspects of generated artifacts are analyzed in the study?\",\"answer\":\"The paper analyzes three dimensions: interface design, template content, and code structure, assessing how they change when only age and gender signals vary in prompts.\"},{\"question\":\"How do the study results address fairness and the personalization–bias boundary?\",\"answer\":\"Controlled experiments on 800 AI-generated websites and an observational study with 20 participants show that developer attributes can meaningfully affect generated software, supporting an underexplored tension between personalization and fairness in AI-assisted programming.\"}]",1784200135,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"biased-or-personalized-the-impact-of-personal-information-on-ai-driven-development","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/biased-or-personalized-the-impact-of-personal-information-on-ai-driven-development/84998/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-24","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the paper investigate about personalized AI coding assistants?","Question",{"text":75,"@type":76},"It investigates how inferred developer demographic characteristics can influence generated software artifacts beyond the stated requirements, potentially embedding bias into code and design outputs.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which aspects of generated artifacts are analyzed in the study?",{"text":80,"@type":76},"The paper analyzes three dimensions: interface design, template content, and code structure, assessing how they change when only age and gender signals vary in prompts.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the study results address fairness and the personalization–bias boundary?",{"text":84,"@type":76},"Controlled experiments on 800 AI-generated websites and an observational study with 20 participants show that developer attributes can meaningfully affect generated software, supporting an underexplored tension between personalization and fairness in AI-assisted programming.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]