[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-267745-105":59,"doc-detail-267745-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","evaluating-llms-as-tools-to-support-early-vocabulary-learning","Evaluating LLMs as Tools to Support Early Vocabulary Learning","","Early language development and children’s vocabulary size strongly predict later well-being, including emotional development and academic outcomes. Because story sharing with caregivers provides word exposure that many children may not get from everyday life, automatically generating targeted storybooks with Large Language Models (LLMs) offers a scalable personalization approach. This study evaluates parent acceptability of LLM-generated stories and children’s ability to learn target vocabulary through shared reading, reporting positive learning outcomes and engaging, educational perceptions.",{"@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/evaluating-llms-as-tools-to-support-early-vocabulary-learning/267745/",{"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/evaluating-llms-as-tools-to-support-early-vocabulary-learning/267745.png","ImageObject",300,407,{"name":92,"@type":93},"Xiajie","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-10","2026-09-14",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",15,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why is early vocabulary learning considered important?","Question",{"text":113,"@type":114},"Vocabulary size in early childhood predicts later reading and academic achievement, and it is also linked to self-regulation and emotional/behavioral outcomes.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How do Large Language Models support vocabulary interventions in this work?",{"text":118,"@type":114},"LLMs enable automatically generating storybooks tailored to learners’ needs and interests, including stories that target specific vocabulary words.",{"name":120,"@type":111,"acceptedAnswer":121},"What does the study evaluate about automatically generated stories?",{"text":122,"@type":114},"The study evaluates (1) whether parents find LLM-generated stories with targeted words acceptable and (2) whether preschoolers learn the target words from being read those stories.","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},267745,1790751346,{"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":39,"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":46,"preview_page_count":4},8814010472675,"https://avatar.qwps.com/avatar/WGlhamll","Evaluating LLMs as Tools to Support Early Vocabulary Learning  \nJennifer M. Weber ([jennifer.m.ellis@colorado.edu](jennifer.m.ellis@colorado.edu))  \nDepartment of Psychology and Neuroscience, 345 UCB  \nBoulder, CO 80309 USA  \nMaria Valentini ([maria.valentini@colorado.edu](maria.valentini@colorado.edu))  \nDepartment of Computer Science, 430 UCB  \nBoulder, CO 80309 USA  \nTéa Wright ([tea.wright@colorado.edu](tea.wright@colorado.edu))  \nDepartment of Computer Science, 430 UCB  \nBoulder, CO 80309 USA  \nKatharina von der Wense ([katharina.kann@colorado.edu](katharina.kann@colorado.edu))  \nDepartment of Computer Science, 430 UCB  \nBoulder, CO 80309 USA  \nEliana Colunga ([eliana.colunga@colorado.edu](eliana.colunga@colorado.edu))  \nDepartment of Psychology and Neuroscience, 345 UCB  \nBoulder, CO 80309 USA  \nAbstract  \nEarly language development, and vocabulary size specifically, is a predictor of well-being later in life, such as emotional development and academic achievement. Many successful vocabulary interventions for young children involve sharing a book with a caregiver, because storybooks are a good source of vocabulary that one might not otherwise encounter in everyday life. With the advent of Large Language Models (LLM), automatically generating stories has become a feasible way to tailor materials to the needs and interests of individual learners. Here we evaluate 1) whether parents of preschoolers find automatically generated stories containing specific vocabulary target words acceptable, and 2) whether preschoolers can learn these target words from being read the automatically generated stories. We find that parents overall consider automatically generated stories engaging, ageappropriate, and educational. In addition, children successfully learn the target words in the storybooks (compared to control words drawn from books not read) . We conclude with a discussion on future work to improve the effectiveness of automatically generated stories to support robust vocabulary learning.  \nKeywords: LLMs; children’s stories; word-learning  \nBackground  \nOne of the main tasks in a young child’s life is to learn the language of their environment. Though many children do this seemingly effortlessly, those that struggle with vocabulary development may be set up for inequities throughout life. For example, vocabulary size at age two is related to reading and academic achievement in elementary school and beyond (Fewell & Deutscher, 2004), and those that fall behind even prior to school entry continue to evince lower reading, writing, and oral language skills through middle and highschool compared to their peers (Rescorla, 2000; Rescorla, 2009) . In fourth grade, estimates suggest that students in the lowest quartile for vocabulary size know less than half the  \nwords students in the highest quartile know, with this difference lasting into adulthood (Biemiller & Slomin, 2001; Brystbaert et al., 2016). Further, vocabulary size upon school entry predicts both vocabulary growth through 10th grade and college GPA (Duff et al., 2015; Masrai & Milton, 2021) . Aside from the effects on language development and language-related academic achievement (e.g., literacy), vocabulary size is related to other measures of wellbeing. For example, two-year-olds with larger vocabularies display better self-regulation skills when they start kindergarten (Morgan et al., 2015), and children with relatively small vocabularies in kindergarten are more likely to have behavioral and emotional problems through their teenage years (Westrup et al., 2019) . Intervening early to take advantage of this self-reinforcing loop and increasing access to vocabulary-enriching materials is critical to closing these vocabulary gaps.  \nThere is considerable evidence that book-rich environments are related to larger vocabularies and early literacy skills. Many initiatives to increase book access and print-rich environments from birth have been implemented over the past 20 years ","cbCaitwXIk1ik1rR","https://ap.wps.com/l/cbCaitwXIk1ik1rR","pdf",259101,"English","# Abstract\n# Background\n## Vocabulary development and well-being\n## Book-rich environments\n## Vocabulary interventions and shared reading\n# Study focus and evaluation","[{\"question\":\"Why is early vocabulary learning considered important?\",\"answer\":\"Vocabulary size in early childhood predicts later reading and academic achievement, and it is also linked to self-regulation and emotional/behavioral outcomes.\"},{\"question\":\"How do Large Language Models support vocabulary interventions in this work?\",\"answer\":\"LLMs enable automatically generating storybooks tailored to learners’ needs and interests, including stories that target specific vocabulary words.\"},{\"question\":\"What does the study evaluate about automatically generated stories?\",\"answer\":\"The study evaluates (1) whether parents find LLM-generated stories with targeted words acceptable and (2) whether preschoolers learn the target words from being read those stories.\"}]","Evaluating LLMs as Tools to Support Early Vocabulary Learning | PDF",1789424621]