An Automatic Assessment Method for the Difficulty of Chinese Primary School Mathematics Application Questions Based on Cognitive Load Theory

An Automatic Assessment Method for the Difficulty of Chinese Primary School Mathematics Application Questions Based on Cognitive Load Theory | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article An Automatic Assessment Method for the Difficulty of Chinese Primary School Mathematics Application Questions Based on Cognitive Load Theory Xiaohui Dong, Quanxin Hou This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7845516/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Automated assessment of question difficulty (QDA) is a key supporting technology in the field of educational assessment, which is of crucial significance for improving the efficiency and fairness of educational assessment. However, in the field of mathematics, the existing QDA methods still face three challenges: (1) Lack of labeled data: The mainstream machine learning methods rely on real difficulty labels, but the commonly used datasets (such as Math23K, Ape210K) lack such labels, and the cost of manual labeling is high and the quality is difficult to guarantee; (2) Contradictions in feature modeling: The existing difficulty features of questions mostly originate from educational and psychological theories, and there are questions where some difficulty features cannot be automatically extracted and calculated; (3) Complex experimental verification: The difficulty of mathematics application questions covers features such as question length, syntax, and reasoning, as well as features such as the concealment of conditions, and different difficulty features require appropriate automatic extraction and calculation methods. In addition, differences in feature selection lead to poor comparability of assessment results. To address these issues, this study proposes the CLT-Math difficulty feature model based on the cognitive load theory, and combines the LLM adaptive learning optimization (LLM-ALO) method to construct the Math Question Difficulty Assessment-Large Language Model (MQDA-LLMA) automatic identification framework. CLT-Math and MQDA-LLMA together form the systematic framework of Math Question Difficulty Assessment (MQDA), achieving precise identification of text features and efficient generation of mathematical expressions and answers. Experiments show that the MQDA framework can train an assessment model with an accuracy of 0.908 on Math23K using only a small number of samples (significantly reducing the labeling cost), and its generalization performance on Ape210K verifies its effectiveness, and the correlation analysis further confirms the rationality of the difficulty feature model. Question difficulty assessment Chinese mathematical application questions LLM Assessment method Cognitive load theory Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7845516","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":551213438,"identity":"24fa7189-5de2-4b22-bf50-4190f7b81ab3","order_by":0,"name":"Xiaohui Dong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAqUlEQVRIiWNgGAWjYDCCAzyMD6BMA6K1MMOUEq+FTYI0LXw3co9VF7bdSWxgb94mwVBzh7AWyTPn0m7PbHuW2MBzrEyC4dgzwloMjveY3ebddjixQSLHTIKx4TARWg7zmBWDtci/IVYL0BZmiC08RGqRPHPGWJr332HjNp60YouEY0Ro4buRY/iZ58xh2X72wxtvfKghQgscsIGIBBI0jIJRMApGwSjAAwDRZDnMv71haQAAAABJRU5ErkJggg==","orcid":"","institution":"NWNU","correspondingAuthor":true,"prefix":"","firstName":"Xiaohui","middleName":"","lastName":"Dong","suffix":""},{"id":551213439,"identity":"8021e1c9-6193-4d94-955e-392ff614d6c7","order_by":1,"name":"Quanxin Hou","email":"","orcid":"","institution":"NWNU","correspondingAuthor":false,"prefix":"","firstName":"Quanxin","middleName":"","lastName":"Hou","suffix":""}],"badges":[],"createdAt":"2025-10-13 07:08:23","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7845516/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7845516/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":96920996,"identity":"794fb84a-c807-4c40-b439-c1e2572a85f6","added_by":"auto","created_at":"2025-11-27 14:15:34","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3657571,"visible":true,"origin":"","legend":"","description":"","filename":"Access1105.docx","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/2e4f2e07788917419e24bc83.docx"},{"id":96906745,"identity":"0168ab87-902c-4ec9-8db7-1dea85bc4b2f","added_by":"auto","created_at":"2025-11-27 12:28:17","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4809,"visible":true,"origin":"","legend":"","description":"","filename":"5f3057010add44389b649c06f7b60530.json","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/55dc047c8880692b20af54fb.json"},{"id":96906766,"identity":"9db8f924-3a3d-4838-aa33-8af0cc8b3d82","added_by":"auto","created_at":"2025-11-27 12:28:18","extension":"docx","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3549358,"visible":true,"origin":"","legend":"","description":"","filename":"figures.docx","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/e91bd7ce0d8eb645e54417bf.docx"},{"id":96906747,"identity":"9e1cdfac-f4b0-480d-b2c7-232ae39d7327","added_by":"auto","created_at":"2025-11-27 12:28:18","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":147041,"visible":true,"origin":"","legend":"","description":"","filename":"5f3057010add44389b649c06f7b605301enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/b7836de3fe8244406c221138.xml"},{"id":96906748,"identity":"ad2f5530-9344-4d08-856d-b028a4e07b36","added_by":"auto","created_at":"2025-11-27 12:28:18","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":119171,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/1170863c69dcc056349e3ce7.png"},{"id":96906746,"identity":"6b1ad239-43fa-4522-b379-4cc327cb3e0a","added_by":"auto","created_at":"2025-11-27 12:28:18","extension":"jpeg","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21377,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage10.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/6b3491b1dbdddec75928dde5.jpeg"},{"id":96919820,"identity":"3ffef5cc-5329-42f6-bfbb-1e2b6d64ac6c","added_by":"auto","created_at":"2025-11-27 14:14:32","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1744600,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/40215f8327f159365d4ef29c.png"},{"id":96920382,"identity":"4cf6d22c-73a3-43ed-ba97-2d4f238bfb16","added_by":"auto","created_at":"2025-11-27 14:15:07","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":84001,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/797c2d54e32e9fc7eb46e70e.png"},{"id":96920069,"identity":"856d7773-2063-4645-9dfb-05cd187daf63","added_by":"auto","created_at":"2025-11-27 14:14:44","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":524584,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/92a7e6ced5d7d15e2fdc0636.png"},{"id":96906762,"identity":"13ec3ebd-4ca8-475a-b803-ea33b579b18c","added_by":"auto","created_at":"2025-11-27 12:28:18","extension":"jpeg","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":138140,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/19d9eea20ee64e82015446ab.jpeg"},{"id":96920874,"identity":"0293b576-56b7-4fe8-9cd9-30fd71ebc202","added_by":"auto","created_at":"2025-11-27 14:15:28","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":270245,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/f22bce55c19742faf8e1fcfe.png"},{"id":96906756,"identity":"bcb92a96-114d-43cd-8df0-817f03e2de4a","added_by":"auto","created_at":"2025-11-27 12:28:18","extension":"jpeg","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":208236,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/6f56b7f32dd8208084d3f45f.jpeg"},{"id":96906755,"identity":"15e50751-ad34-471e-9c9d-e1f222d71d5f","added_by":"auto","created_at":"2025-11-27 12:28:18","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":36509,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/13f05b57430b969989b19be8.png"},{"id":96920528,"identity":"321d7c9e-092b-4322-8d41-97cceb4667e7","added_by":"auto","created_at":"2025-11-27 14:15:15","extension":"jpeg","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":20839,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/780960cde804478998e78a3f.jpeg"},{"id":96919883,"identity":"80974b8a-5e40-4983-80c2-0940f539227a","added_by":"auto","created_at":"2025-11-27 14:14:34","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30737,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/982677d78de7b92d9967c099.png"},{"id":96906751,"identity":"8c2cf7d0-5988-4018-8b6a-59c89b26783b","added_by":"auto","created_at":"2025-11-27 12:28:18","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17754,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage10.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/3c42c52c1d84bc7da9f8a31e.png"},{"id":96920394,"identity":"6841e3ce-c097-4bb5-a35a-14e4bb7ff2a9","added_by":"auto","created_at":"2025-11-27 14:15:07","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":153074,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/be0100f8d6d1f59fb24a8bb6.png"},{"id":96920807,"identity":"32d31102-22ed-4abf-bb2b-cdc8181477ac","added_by":"auto","created_at":"2025-11-27 14:15:26","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17991,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/29fd64ed97bf17b9d67f88a2.png"},{"id":96906765,"identity":"c07bc0c9-a1cd-451e-bd5c-c70d12355fa9","added_by":"auto","created_at":"2025-11-27 12:28:18","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":52346,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/10c87fb0480105a20e82cc12.png"},{"id":96920760,"identity":"d49d7510-999e-40ab-9462-017c8e899283","added_by":"auto","created_at":"2025-11-27 14:15:24","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30730,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/5047870186d3e02b4957aed5.png"},{"id":96906767,"identity":"602912da-6b6f-41a5-99df-d21f3853c0bf","added_by":"auto","created_at":"2025-11-27 12:28:18","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":31821,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/e5a016cb40167e8a58d17bbf.png"},{"id":96919992,"identity":"fa26cf70-1c72-4b03-b933-a4278d62c5f7","added_by":"auto","created_at":"2025-11-27 14:14:40","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":53254,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/fb420e49bd43a60e769ea696.png"},{"id":96906769,"identity":"17f09995-2cba-4cd1-ae51-cd9a242ea9ac","added_by":"auto","created_at":"2025-11-27 12:28:18","extension":"png","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9822,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/ee6527189d9b7620ffb45eb9.png"},{"id":96921084,"identity":"b0c8d444-12ab-4f8a-b173-e76ecdae9f8d","added_by":"auto","created_at":"2025-11-27 14:15:41","extension":"png","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":12344,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/fb5888703e8373a11ed9907c.png"},{"id":96906770,"identity":"932afe32-808c-4bf4-9c8f-719252fe9579","added_by":"auto","created_at":"2025-11-27 12:28:18","extension":"xml","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":144259,"visible":true,"origin":"","legend":"","description":"","filename":"5f3057010add44389b649c06f7b605301structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/4584c3a9afd3483e7cfe9500.xml"},{"id":96906771,"identity":"bae69f27-8caf-453d-8d84-763f4cad6165","added_by":"auto","created_at":"2025-11-27 12:28:18","extension":"html","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":159581,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1/8184ffc7faf3dd29e17dc0ac.html"},{"id":100238744,"identity":"a6035f4c-9deb-4b52-9d3e-c330cd88a3aa","added_by":"auto","created_at":"2026-01-14 12:55:34","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":857771,"visible":true,"origin":"","legend":"","description":"","filename":"Access1105.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7845516/v1_covered_5d71c047-a8ed-41db-b22f-73ac499ad2a2.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"An Automatic Assessment Method for the Difficulty of Chinese Primary School Mathematics Application Questions Based on Cognitive Load Theory","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Question difficulty assessment, Chinese mathematical application questions, LLM, Assessment method, Cognitive load theory","lastPublishedDoi":"10.21203/rs.3.rs-7845516/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7845516/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAutomated assessment of question difficulty (QDA) is a key supporting technology in the field of educational assessment, which is of crucial significance for improving the efficiency and fairness of educational assessment. However, in the field of mathematics, the existing QDA methods still face three challenges: (1) Lack of labeled data: The mainstream machine learning methods rely on real difficulty labels, but the commonly used datasets (such as Math23K, Ape210K) lack such labels, and the cost of manual labeling is high and the quality is difficult to guarantee; (2) Contradictions in feature modeling: The existing difficulty features of questions mostly originate from educational and psychological theories, and there are questions where some difficulty features cannot be automatically extracted and calculated; (3) Complex experimental verification: The difficulty of mathematics application questions covers features such as question length, syntax, and reasoning, as well as features such as the concealment of conditions, and different difficulty features require appropriate automatic extraction and calculation methods. In addition, differences in feature selection lead to poor comparability of assessment results. To address these issues, this study proposes the CLT-Math difficulty feature model based on the cognitive load theory, and combines the LLM adaptive learning optimization (LLM-ALO) method to construct the Math Question Difficulty Assessment-Large Language Model (MQDA-LLMA) automatic identification framework. CLT-Math and MQDA-LLMA together form the systematic framework of Math Question Difficulty Assessment (MQDA), achieving precise identification of text features and efficient generation of mathematical expressions and answers. Experiments show that the MQDA framework can train an assessment model with an accuracy of 0.908 on Math23K using only a small number of samples (significantly reducing the labeling cost), and its generalization performance on Ape210K verifies its effectiveness, and the correlation analysis further confirms the rationality of the difficulty feature model.\u003c/p\u003e","manuscriptTitle":"An Automatic Assessment Method for the Difficulty of Chinese Primary School Mathematics Application Questions Based on Cognitive Load Theory","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-27 12:28:13","doi":"10.21203/rs.3.rs-7845516/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"32c4fa04-a28d-4ad5-a8d6-4658e517f4dd","owner":[],"postedDate":"November 27th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-01-14T12:54:56+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-27 12:28:13","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7845516","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7845516","identity":"rs-7845516","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}