[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-585324-105":59,"doc-detail-585324-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","comparing-expert-and-ai-based-assessments-in-evaluating-learner-knowledge","Comparing Expert and AI-Based Assessments in Evaluating Learner Knowledge","","Rapid progress in large language models (LLMs) creates new opportunities for educational assessment through AI-generated evaluation tools. This paper compares expert-created assessments with LLM-generated assessments to measure effectiveness in evaluating learner knowledge, focusing on computer science and project management. The study contrasts item generation, alignment with curriculum objectives, and the resulting implications for validity, reliability, and educational value, outlining strengths, limitations, and guidance for responsible AI integration in learning environments.",{"@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/comparing-expert-and-ai-based-assessments-in-evaluating-learner-knowledge/585324/",{"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/comparing-expert-and-ai-based-assessments-in-evaluating-learner-knowledge/585324.png","ImageObject",300,407,{"name":92,"@type":93},"Aria Callaghan","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-05","2026-10-15",true,{"@type":102,"interactionType":103,"userInteractionCount":24},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"What is the main goal of comparing expert and LLM-generated assessments?","Question",{"text":112,"@type":113},"To evaluate how effectively expert-created and AI-based assessments measure learner knowledge, with a focus on computer science and project management.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"Why do researchers question whether AI-generated assessments are as reliable as expert-designed ones?",{"text":117,"@type":113},"Because AI-based item generation may raise concerns about validity, reliability, and educational value, even when studies show comparable student performance.",{"name":119,"@type":110,"acceptedAnswer":120},"How do experts and LLMs work together in the proposed assessment process?",{"text":121,"@type":113},"Experts first develop assessments using their subject-matter knowledge, then apply prompt engineering so an LLM generates a parallel version on the same topic for comparison and analysis.","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},585324,1793152595,{"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":24,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":19,"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":52,"preview_page_count":4},962084926284,"https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0","COMPARING EXPERT AND AI-BASED ASSESSMENTSIN EVALUATING LEARNER KNOWLEDGE  \nMohamad Al Assaad and Houssam Kanso  \nTalan Research and Innovation Center  \nParis, France  \nABSTRACT  \nThe rapid development of large language models (LLMs) has introduced new possibilities for educational assessment, particularly in the creation of learner evaluation tools. Traditionally, expert-designed tests have been the standard for assessing knowledge, relying on subject-matter expertise, pedagogical principles, and alignment with curriculum objectives. In contrast, LLMs such as ChatGPT can now generate assessment items on demand, offering scalability and adaptability but raising questions about validity, reliability, and educational value. This paper compares expert-created assessments with LLM-generated assessments to evaluate their effectiveness in measuring learner knowledge, in the computer science and project management fields. Through this comparison, we aim to highlight both the strengths and limitations of AI-based assessment generation and evaluation. The findings have implications for the future of educational assessment design, teacher practice, and the responsible integration of AI in learning environments.  \nKEYWORDS  \nArtificial Intelligence, Large Language Models (LLMs), AI-Generated Assessments, Expert-Created Assessment, Learner Knowledge Evaluation, Personalized Assessment  \n1. INTRODUCTION  \nArtificial Intelligence (AI) and, more specifically, large language models (LLMs) are increasingly shaping the landscape of education. From intelligent tutoring systems to automated content generation, these technologies are being integrated into teaching and learning practices to provide scalable, adaptive, and personalized experiences. Among their emerging applications, LLMs offer novel possibilities for assessment design, enabling educators to create tests and evaluation materials that are personalized to individual learners’ needs. Such adaptive approaches have potential in supporting teachers by reducing workload while simultaneously enhancing the personalization of learning pathways.  \nFor a long time, expert-designed assessments were the standard in evaluating learner knowledge. These assessments are grounded in subject-matter expertise, curriculum objectives, and pedagogical rigor. However, the rapid progress of LLMs and their use in adaptive learning raises important questions. Can AI-generated assessments achieve a comparable level of quality, validity, and reliability in expert-designed assessments? For example, a recent comparative study of MCQs in programming education found that GPT-4-generated items had clarity, strong distractors, and alignment with learning objectives (Liu et al, 2023) . Research on AI-generated exam questions (the “single best answer” type, like multiple-choice with one correct option) found that students performed the same on these questions whether they were written by humans or created by AI. In other words, AI-made questions were just as good as human ones when it came to testing students fairly and distinguishing between stronger and weaker students (Kalra et al, 2025) . Furthermore, systematic reviews of prompt engineering indicate that the way we instruct LLMs (i.e., prompt design) has a substantial effect on educational outcomes and alignment with learning objectives (Thammathong and Debuse, 2025) .  \nAssessment in education has been studied from multiple perspectives, including traditional expert-designed assessments, adaptive assessment systems, AI/LLM-generated assessments, and cognitive diagnostic approaches. One important area is adaptive assessment, which dynamically adjusts to learners’ responses. A recent systematic review catalogued adaptive assessment methods and highlighted implementation challenges across domains (Hamoud and Abusham, 2025) . In the AI/LLM domain, several reviews have examined the growing role of automated assessment tools. For instance, a review of AI-based assessment ","cbCaijJxaO6ZRWva","https://ap.wps.com/l/cbCaijJxaO6ZRWva","pdf",883451,"English","# Abstract\n# Introduction\n## Background and Motivation\n## Related Work: Expert, Adaptive, and AI/LLM Assessment\n# Comparative Study Approach","[{\"question\":\"What is the main goal of comparing expert and LLM-generated assessments?\",\"answer\":\"To evaluate how effectively expert-created and AI-based assessments measure learner knowledge, with a focus on computer science and project management.\"},{\"question\":\"Why do researchers question whether AI-generated assessments are as reliable as expert-designed ones?\",\"answer\":\"Because AI-based item generation may raise concerns about validity, reliability, and educational value, even when studies show comparable student performance.\"},{\"question\":\"How do experts and LLMs work together in the proposed assessment process?\",\"answer\":\"Experts first develop assessments using their subject-matter knowledge, then apply prompt engineering so an LLM generates a parallel version on the same topic for comparison and analysis.\"}]","Comparing Expert and AI-Based Assessments in Evaluating Learner Knowledge | PDF",1792054383]