Cross-Domain Knowledge Transfer without Retraining to Facilitating Seamless Knowledge Application in Large Language Models

Cross-Domain Knowledge Transfer without Retraining to Facilitating Seamless Knowledge Application in Large Language Models | 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 Cross-Domain Knowledge Transfer without Retraining to Facilitating Seamless Knowledge Application in Large Language Models Jae Hoon Kim, Hye Rin Kim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4328966/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 Cross-domain knowledge transfer in large language models (LLMs) presents significant challenges, particularly regarding the extensive resources required for retraining. This research introduces innovative embedding adaptation and context adjustment techniques that enable LLMs to efficiently transfer knowledge across diverse domains without the need for comprehensive retraining. Experimental results demonstrate improved model flexibility and reduced computational demands, highlighting the potential for rapid deployment and scalability. These findings suggest a sustainable approach to deploying adaptive AI across various sectors, significantly impacting future developments in artificial intelligence. Artificial Intelligence and Machine Learning Large Language Models Knowledge Transfer Domain Adaptation Embedding Techniques Computational Efficiency Sustainable AI Full Text Additional Declarations The authors declare no competing interests. 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-4328966","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":295786071,"identity":"dec47886-5132-4b19-ae33-3f79ec39aeff","order_by":0,"name":"Jae Hoon Kim","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8UlEQVRIiWNgGAWjYBACxgYGNgiLB8j82AAWazxAtBbGmQ0MEiAxvFqAAKaFgYGZF6yFgQGvFub2w8cefKi4A9RyuHWz7Q6bOt32w0BbamyicTqsJy3dcMaZZwwMvI1tt3PPpEmYnUkEajmWltuA0y85ZtK8bYcZGPgZgVraDkuYHQBqYWw4jFtL//tvCC2WIC3nHxLQMiOHDaIF5DBGkJYbhGyZ8cxMcsYZoBaeg203e9vSJLfdANqSgMcvhv3JzyQ+VIC0pD+78bPNht/sfPrDBx9qbHBrgUrU7z+ALJyAQzkIyOORGwWjYBSMglEAAQB/VWJZh0HJDAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0009-0003-4429-7707","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Jae","middleName":"Hoon","lastName":"Kim","suffix":""},{"id":295786072,"identity":"21a80338-7f1f-4637-bdba-88f474d50fed","order_by":1,"name":"Hye Rin Kim","email":"","orcid":"https://orcid.org/0009-0009-7779-6055","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Hye","middleName":"Rin","lastName":"Kim","suffix":""}],"badges":[],"createdAt":"2024-04-26 10:35:52","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-4328966/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4328966/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":55477110,"identity":"5088e523-b1ac-4996-af93-965469c2072b","added_by":"auto","created_at":"2024-04-29 02:52:05","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":236048,"visible":true,"origin":"","legend":"","description":"","filename":"submission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4328966/v1_covered_74884a67-6aeb-493b-b251-eea2f9a8c3fa.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eCross-Domain Knowledge Transfer without Retraining to Facilitating Seamless Knowledge Application in Large Language Models\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"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":"Large Language Models, Knowledge Transfer, Domain Adaptation, Embedding Techniques, Computational Efficiency, Sustainable AI","lastPublishedDoi":"10.21203/rs.3.rs-4328966/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4328966/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eCross-domain knowledge transfer in large language models (LLMs) presents significant challenges, particularly regarding the extensive resources required for retraining. This research introduces innovative embedding adaptation and context adjustment techniques that enable LLMs to efficiently transfer knowledge across diverse domains without the need for comprehensive retraining. Experimental results demonstrate improved model flexibility and reduced computational demands, highlighting the potential for rapid deployment and scalability. These findings suggest a sustainable approach to deploying adaptive AI across various sectors, significantly impacting future developments in artificial intelligence.\u003c/p\u003e","manuscriptTitle":"Cross-Domain Knowledge Transfer without Retraining to Facilitating Seamless Knowledge Application in Large Language Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-29 02:43:57","doi":"10.21203/rs.3.rs-4328966/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":"b8813829-07b6-4460-94eb-91ce85378e65","owner":[],"postedDate":"April 29th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":31194181,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2024-04-29T02:43:57+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-29 02:43:57","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4328966","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4328966","identity":"rs-4328966","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}