[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-273645-105":59,"doc-detail-273645-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","are-llms-becoming-similarly-creative-evidence-from-three-years-of-models-paper","Are LLMs becoming similarly creative? Evidence from three years of models - paper","","Many benchmarks evaluate Large Language Models (LLMs) on tasks with verifiable answers, yet open-ended performance—where creativity, originality, and diversity are central—has been less systematically tracked over time. This paper analyzes creative outputs across three years of model releases, using responses to Infinity-Chat100 real user queries and the Alternate Uses Task. Sentence-embedding similarity is used to measure semantic trends. Results show a statistically significant decline in output diversity over time.",{"@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/are-llms-becoming-similarly-creative-evidence-from-three-years-of-models-paper/273645/",{"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/are-llms-becoming-similarly-creative-evidence-from-three-years-of-models-paper/273645.png","ImageObject",300,407,{"name":92,"@type":93},"Miles","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-25","2026-09-15",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",12,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What question does the paper investigate about LLM creativity?","Question",{"text":113,"@type":114},"It examines whether LLMs are becoming similarly creative over time, meaning that creative outputs may grow more homogeneous across generations and models.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the paper measure creativity-related trends in model outputs?",{"text":118,"@type":114},"It computes sentence-embedding similarity to analyze how responses change across model releases when answering open-ended creative prompts.",{"name":120,"@type":111,"acceptedAnswer":121},"Which datasets or prompt sources are used in the study?",{"text":122,"@type":114},"The study uses Infinity-Chat100, a real-world collection of open-ended user queries, and the Alternate Uses Task, a standardized psychometric creativity assessment.","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},273645,1790485987,{"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":105,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":41,"preview_page_count":4},13056703019404,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","arXiv : 2608 . 19437v 1 [cs .CL] 19 Aug 2026  \nAre LLMs becoming similarly creative? Evidence from three years of models  \nNirav Patel 1 ∗ Josiah Crossman 1 Eva Aggarwal 1 Emily Wenger 1 ,2  \n1Department of Computer Science, Duke University  \n2Department of Electrical & Computer Engineering, Duke University  \nAbstract  \nMany benchmarks track Large Language Model (LLM) performance on tasks with verifiable answers, but less is known about how LLM performance is evolving on open-ended tasks, where creativity, originality and diversity may matter as much as quality. As LLMs increasingly support human ideation and creative work, understanding trends in LLM performance on open-ended tasks is critical. This paper presents a preliminary analysis of LLM creative outputs spanning three years of model releases, examining model responses to Infinity-Chat100, a real-world collection of open-ended user queries, and the Alternate Uses Task, an established psychometric creativity assessment. Using sentence-embedding similarity, we examine trends in LLM responses to these prompts. Our findings show a statistically significant decrease in model output diversity over time, suggesting that LLM outputs may be converging in creative substance across models. If this trend persists, LLM-driven homogenization may progressively diminish human agency in human-AI co-creative work, demanding careful consideration of LLMs’ role in the human creative process.  \n1 Introduction  \nIn a few short years, conversational AI systems powered by large language models (LLMs) have moved from experimental prototypes to widely-used everyday tools. By July 2025, ChatGPT had more than 700 million weekly active users, who collectively sent more than 2.5 billion messages per day, or roughly 29,000 messages per second [1] . Anthropic and DeepSeek, other popular AI chatbot providers, similarly have tens of millions of users [2, 3] .  \nStudies show a wide variety of use cases for LLM-powered products, but creativity-relevant tasks like writing, content creation, and research are common. Approximately 70% of consumer ChatGPT use is non-work-related, with practical guidance (a category which includes “creative ideation”) and writing accounting for over half of ChatGPT messages [1] . Similarly, Anthropic estimates that nearly 20% of Claude messages fall into categories like “content creation” or “multidisciplinary academic research and writing.” [4] . As LLMs mediate more creative work, it is critical to understand how these systems affect the range of ideas users encounter and how model-generated outputs may shape downstream human creativity.  \nA growing body of research suggests that LLM outputs can appear individually creative but are often collectively homogeneous—similar either to other “creative” content produced by the same LLM or content produced by other LLMs. In one study of AI-assisted creative writing, writers with access to AI-generated ideas produced stories that were judged as more creative and better written than stories from writers working alone. However, the AI-assisted stories were also more similar to one another than stories written without AI assistance [5] . Across real-world open-ended queries, models  \n∗ Corresponding author: [nirav.patel@duke.edu](nirav.patel@duke.edu)  \nPreprint.  \nexhibit both intra-model repetition and inter-model convergence [6] . Human baseline studies on standardized divergent thinking tasks again surface this pattern, finding that LLM outputs have similar or higher creativity scores than humans on these tasks but are substantially less diverse [7, 8, 9] . Algorithmic monoculture has long been a subject of academic concern (e.g. [10, 11]), and observed homogeneity across AI creative outputs represents yet another facet of this well-documented problem. However, it remains unclear whether this homogeneity is a temporary byproduct of a still-developing technology or an inevitable—potentially compounding [12]—feature of statistical lan","cbCailTCiuWjjWVv","https://ap.wps.com/l/cbCailTCiuWjjWVv","pdf",1151747,"English","# Introduction\n## Motivation and prior work\n## Benchmarks and evaluation gap\n## Contribution","[{\"question\":\"What question does the paper investigate about LLM creativity?\",\"answer\":\"It examines whether LLMs are becoming similarly creative over time, meaning that creative outputs may grow more homogeneous across generations and models.\"},{\"question\":\"How does the paper measure creativity-related trends in model outputs?\",\"answer\":\"It computes sentence-embedding similarity to analyze how responses change across model releases when answering open-ended creative prompts.\"},{\"question\":\"Which datasets or prompt sources are used in the study?\",\"answer\":\"The study uses Infinity-Chat100, a real-world collection of open-ended user queries, and the Alternate Uses Task, a standardized psychometric creativity assessment.\"}]","Are LLMs becoming similarly creative? Evidence from three years of models - paper | PDF",1789472354]