AI-generated estimates of Dutch words and expressions

AI-generated estimates of Dutch words and expressions | 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 AI-generated estimates of Dutch words and expressions Marc Brysbaert, Javier Conde, Juan Haro, Carlos Arriaga, Pedro Reviriego This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8058427/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 10 You are reading this latest preprint version Abstract This study introduces and validates GPT_FAM, an AI-generated resource of familiarity estimates for 935,000 Dutch words and 201,000 multiword expressions. Based on previous studies, we hypothesized that such estimates, particularly when fine-tuned using a few thousand human ratings, would offer a useful, scalable measure of verbal knowledge. The results confirmed the expectation, showing that fine-tuned GPT estimates correlate well with word prevalence, reflecting the likelihood of word recognition. Equally importantly, GPT_FAM estimates significantly predict response latencies in lexical decision tasks, emerging as the most robust predictor in a random forest analysis alongside word frequency and length. The measure may be especially useful for assessing the difficulty of morphologically complex items, such as inflected word forms and transparent compounds, where traditional frequency metrics tend to be ineffective. Both untuned and fine-tuned estimates are freely available for research and educational purposes. Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 28 Apr, 2026 Reviews received at journal 14 Apr, 2026 Reviews received at journal 06 Apr, 2026 Reviewers agreed at journal 23 Mar, 2026 Reviewers agreed at journal 19 Mar, 2026 Reviewers agreed at journal 17 Mar, 2026 Reviewers invited by journal 17 Mar, 2026 Editor assigned by journal 01 Feb, 2026 Submission checks completed at journal 18 Nov, 2025 First submitted to journal 07 Nov, 2025 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-8058427","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":608484904,"identity":"7f454d98-a57d-419f-9139-2538645e51f9","order_by":0,"name":"Marc Brysbaert","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA+UlEQVRIiWNgGAWjYLACxgYgIQFm2iCJEKclIQ3CJ0XLYcJadNvPPvzAuONe4vzZzQ8fV/44nzjfvff4A8YdNji1mJ1JN5ZgPFOcuOHOMWPDMwm3EzeeOZfYwHgmDbeWA2lsDIxtCYkbJBLMJBtAWmbkGDYwth3GreX8M4iW+TPSv/9sSDiXuHH+G5CW/7i13IDa0nAjx4yxIeFA4nwJHpCWA3i0PGOWSDyTYLzhzpliyYa0ZOMNPDmGMxLPJONxWBrjh487EmTnz27f+LHBxk52fvsZA6CIHU4tYJDAwODYAOMYHICIEAT2cJZ8A25Vo2AUjIJRMDIBAJCEYGbWFwo5AAAAAElFTkSuQmCC","orcid":"","institution":"Ghent University","correspondingAuthor":true,"prefix":"","firstName":"Marc","middleName":"","lastName":"Brysbaert","suffix":""},{"id":608484905,"identity":"ba1ca302-825b-474f-a3f8-1640357ba2ac","order_by":1,"name":"Javier Conde","email":"","orcid":"","institution":"Universidad Politécnica de Madrid","correspondingAuthor":false,"prefix":"","firstName":"Javier","middleName":"","lastName":"Conde","suffix":""},{"id":608484906,"identity":"c9a805c9-c1ec-4f4b-b945-d8e504d07ca2","order_by":2,"name":"Juan Haro","email":"","orcid":"","institution":"Universitat Rovira I Virgili","correspondingAuthor":false,"prefix":"","firstName":"Juan","middleName":"","lastName":"Haro","suffix":""},{"id":608484908,"identity":"7ec4acee-95c5-49d0-9ab2-35cbdf3e7bd0","order_by":3,"name":"Carlos Arriaga","email":"","orcid":"","institution":"Universidad Politécnica de Madrid","correspondingAuthor":false,"prefix":"","firstName":"Carlos","middleName":"","lastName":"Arriaga","suffix":""},{"id":608484910,"identity":"d2a51f2b-62e8-4fd9-b7e8-85192fc4ad40","order_by":4,"name":"Pedro Reviriego","email":"","orcid":"","institution":"Universidad Politécnica de Madrid","correspondingAuthor":false,"prefix":"","firstName":"Pedro","middleName":"","lastName":"Reviriego","suffix":""}],"badges":[],"createdAt":"2025-11-07 15:23:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8058427/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8058427/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":105035338,"identity":"1abd353f-6968-4d04-ad26-0a94f9fc0841","added_by":"auto","created_at":"2026-03-20 07:25:53","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":778151,"visible":true,"origin":"","legend":"","description":"","filename":"Dutchfamiliarityratingsforsubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8058427/v1_covered_5abc97b0-9177-4c7f-bc18-05123bcf1e7b.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"AI-generated estimates of Dutch words and expressions","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"language-resources-and-evaluation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"lrev","sideBox":"Learn more about [Language Resources and Evaluation](http://link.springer.com/journal/10579)","snPcode":"10579","submissionUrl":"https://submission.nature.com/new-submission/10579/3","title":"Language Resources and Evaluation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"","lastPublishedDoi":"10.21203/rs.3.rs-8058427/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8058427/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"This study introduces and validates GPT_FAM, an AI-generated resource of familiarity estimates for 935,000 Dutch words and 201,000 multiword expressions. Based on previous studies, we hypothesized that such estimates, particularly when fine-tuned using a few thousand human ratings, would offer a useful, scalable measure of verbal knowledge. The results confirmed the expectation, showing that fine-tuned GPT estimates correlate well with word prevalence, reflecting the likelihood of word recognition. Equally importantly, GPT_FAM estimates significantly predict response latencies in lexical decision tasks, emerging as the most robust predictor in a random forest analysis alongside word frequency and length. The measure may be especially useful for assessing the difficulty of morphologically complex items, such as inflected word forms and transparent compounds, where traditional frequency metrics tend to be ineffective. Both untuned and fine-tuned estimates are freely available for research and educational purposes.","manuscriptTitle":"AI-generated estimates of Dutch words and expressions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-19 12:37:15","doi":"10.21203/rs.3.rs-8058427/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-28T06:52:59+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-14T11:27:26+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-06T13:50:16+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"1374491114503030753445918335154379309","date":"2026-03-23T09:54:37+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"84554242703786163217967507962298883881","date":"2026-03-19T12:16:54+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"209767598334832396045706911357582605898","date":"2026-03-17T23:10:35+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-17T10:14:53+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-02-01T11:49:53+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-11-18T13:22:30+00:00","index":"","fulltext":""},{"type":"submitted","content":"Language Resources and Evaluation","date":"2025-11-07T15:07:43+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"language-resources-and-evaluation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"lrev","sideBox":"Learn more about [Language Resources and Evaluation](http://link.springer.com/journal/10579)","snPcode":"10579","submissionUrl":"https://submission.nature.com/new-submission/10579/3","title":"Language Resources and Evaluation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"862b2500-be68-414b-b794-550dcfc9ca43","owner":[],"postedDate":"March 19th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-04-28T07:10:10+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-19 12:37:15","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8058427","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8058427","identity":"rs-8058427","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}