Parameter-Efficient Fine-Tuning (PEFT) Approaches for Large Language Models: A Comparative Analysis on AG News

Parameter-Efficient Fine-Tuning (PEFT) Approaches for Large Language Models: A Comparative Analysis on AG News | 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 Parameter-Efficient Fine-Tuning (PEFT) Approaches for Large Language Models: A Comparative Analysis on AG News Asmaa Mohammed Shuibi This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7420392/v1 This work is licensed under a CC BY 4.0 License Status: Under Revision Version 1 posted 9 You are reading this latest preprint version Abstract Text classification remains a cornerstone task in Natural Language Processing (NLP), playing a critical role in organizing and understanding large-scale textual data. This study investigates the performance of traditional machine learning algorithms and transformer-based architectures on the AG News dataset, a widely used benchmark for multi-class news classification. In particular, the performance of the DistilBERT model and its Low-Rank Adaptation (LoRA)-enhanced version are examined under a consistent experimental framework that includes different vectorization techniques and parameter configurations. The classical models are evaluated using Count Vectorizer, TF-IDF, Hashing Vectorizer, and semantic embeddings via Word2Vec (CBOW and Skip-gram), while transformer-based models are fine-tuned with varying batch sizes, input lengths, and epochs. The experimental results demonstrate that traditional classifiers, such as Ridge Classifier and Complement Naive Bayes, achieve strong performance when paired with TF-IDF and Count Vectorizer, yielding accuracies exceeding 89% with minimal computational overhead. Meanwhile, the standard DistilBERT model achieved 89.8% accuracy but required over 6 hours of training. By contrast, the LoRA-enhanced DistilBERT attained 90.0% accuracy with a 40% reduction in training time, highlighting the impact of parameter-efficient fine-tuning (PEFT) strategies. These findings underscore the trade-offs between model complexity, computational efficiency, and classification accuracy, and establish LoRA as a practical solution for scalable transformer fine-tuning. . Text Classification AG News DistilBERT LoRA Parameter-Efficient Fine-Tuning (PEFT) Machine Learning NLP TF-IDF Transformer Models Model Optimization Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Revision Version 1 posted Editorial decision: Revision requested 20 Apr, 2026 Reviews received at journal 20 Apr, 2026 Reviews received at journal 10 Apr, 2026 Reviewers agreed at journal 09 Apr, 2026 Reviewers agreed at journal 08 Apr, 2026 Reviewers invited by journal 29 Sep, 2025 Editor assigned by journal 27 Aug, 2025 Submission checks completed at journal 25 Aug, 2025 First submitted to journal 20 Aug, 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-7420392","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":526978712,"identity":"20a2e7da-f130-48e7-b9b3-3d435d8096f3","order_by":0,"name":"Asmaa Mohammed Shuibi","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA3klEQVRIiWNgGAWjYPCCAwxsEoyND6A8A6K1NMOUEqmFQQKoiygt/P2nEz8w/LmT2Cfd3Fbxo+ZwHgN78zYJfFokbuRulmBse5bYJnOw7WbPscPFDDzHyvBqYbjBu0GCseFwYptEYtsNHrbDiQ0SOWZ4tcifP7v5B8MfiJbCP/+AWuTf4NdicCAX6HI2iBZm3jaQLTz4tRjeyN1mkdh22Bjol2Zp2b70YjaetGILfFrkgA678eHPYdn5s9sffnzzzTqPn/3wxhv4tIBBAjKbjaByfNpHwSgYBaNgFIABAPtrT+RnQyAyAAAAAElFTkSuQmCC","orcid":"","institution":"Arab American University","correspondingAuthor":true,"prefix":"","firstName":"Asmaa","middleName":"Mohammed","lastName":"Shuibi","suffix":""}],"badges":[],"createdAt":"2025-08-20 20:08:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7420392/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7420392/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93189266,"identity":"658aff89-df0a-484e-8abe-3a05b297aaf3","added_by":"auto","created_at":"2025-10-10 03:43:38","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":395037,"visible":true,"origin":"","legend":"","description":"","filename":"AGNEWSPAPERfinal.docx","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/9e7ccb146b969089a0318ed6.docx"},{"id":93188516,"identity":"6708e1fd-83a2-476c-aafd-d8c31016716d","added_by":"auto","created_at":"2025-10-10 03:35:38","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3554,"visible":true,"origin":"","legend":"","description":"","filename":"29a4303cc9ac437991bdb9fb3f4ef180.json","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/fcda6db84d6cc115ca6afc66.json"},{"id":93189657,"identity":"de96d727-2011-4c8f-b59a-524017aff334","added_by":"auto","created_at":"2025-10-10 03:51:38","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":89108,"visible":true,"origin":"","legend":"","description":"","filename":"29a4303cc9ac437991bdb9fb3f4ef1801enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/a8188b714f6df233b5278a13.xml"},{"id":93189658,"identity":"547fc11f-484c-4188-a377-6a8a15e9feeb","added_by":"auto","created_at":"2025-10-10 03:51:38","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":63221,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/206b382762f5930d266516d6.png"},{"id":93188519,"identity":"44a4c1b3-759c-4492-be59-3a7ed1004c9d","added_by":"auto","created_at":"2025-10-10 03:35:38","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41632,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/00d801c41113f820d9c73a80.png"},{"id":93189264,"identity":"39cd2147-7d7b-4588-84db-597abb6b7822","added_by":"auto","created_at":"2025-10-10 03:43:38","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":18937,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/80c4002f46c47c91038e84c1.png"},{"id":93188525,"identity":"5ac7612a-9dc2-463a-8c70-14bac8918114","added_by":"auto","created_at":"2025-10-10 03:35:38","extension":"jpeg","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":256779,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/5d9be9d778038ffb96717a97.jpeg"},{"id":93188520,"identity":"54eb1ab3-828d-40f4-8c95-e616d038511a","added_by":"auto","created_at":"2025-10-10 03:35:38","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14048,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/744a345d3c4337f976ec1dd8.png"},{"id":93188522,"identity":"71198d93-422a-4b56-bc03-0db5e2b1a6ef","added_by":"auto","created_at":"2025-10-10 03:35:38","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9872,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/8046686bf015d5dc8697f163.png"},{"id":93190470,"identity":"f15921e3-b4a2-4b87-afab-3e3d33076899","added_by":"auto","created_at":"2025-10-10 03:59:38","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35619,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/5c6be96b51a4dc3d7961ae24.png"},{"id":93189269,"identity":"d23ac323-cbc1-47ec-a7e3-439e02be9401","added_by":"auto","created_at":"2025-10-10 03:43:38","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32220,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/065c8a38a375938199bd4307.png"},{"id":93189272,"identity":"fe34c3d4-2d51-4170-a8bd-33e2a7cd2e13","added_by":"auto","created_at":"2025-10-10 03:43:39","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16202,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/8b8352b376ba3ecdc31c1685.png"},{"id":93188528,"identity":"3ca8b052-0a62-47b1-a7b1-13813d963635","added_by":"auto","created_at":"2025-10-10 03:35:38","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":9512,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/65ced6ba7b11af4284c7de53.png"},{"id":93188537,"identity":"55e9cbc0-8b09-4e82-b46c-15102c136f09","added_by":"auto","created_at":"2025-10-10 03:35:40","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6011,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/cde802a6600a169bb465dc44.png"},{"id":93188534,"identity":"74fa6eac-99b8-4801-a319-b6d39ec32a13","added_by":"auto","created_at":"2025-10-10 03:35:39","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":65781,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/5d06526a529156d00ad87ecd.png"},{"id":93189271,"identity":"938044c2-39d7-4954-980f-4be615886052","added_by":"auto","created_at":"2025-10-10 03:43:39","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":4623,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/b9cb85aef388a0f1318b67d9.png"},{"id":93188527,"identity":"69812a37-15f1-4b39-903e-58ba73eda0d8","added_by":"auto","created_at":"2025-10-10 03:35:38","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":3628,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/7ad0eff99d82445cbc25373b.png"},{"id":93188533,"identity":"6d3f2d7d-3a74-41ae-a638-e1b04a1426db","added_by":"auto","created_at":"2025-10-10 03:35:39","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7106,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/c5c81989b4b969526e1d4427.png"},{"id":93188538,"identity":"4bcf8908-2dda-40e0-9a61-02898422b577","added_by":"auto","created_at":"2025-10-10 03:35:40","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6831,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/14ea0038e0bfd2776861ed44.png"},{"id":93188530,"identity":"27055dae-d4f6-40ad-9ee2-fe4b4529b713","added_by":"auto","created_at":"2025-10-10 03:35:39","extension":"xml","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":88386,"visible":true,"origin":"","legend":"","description":"","filename":"29a4303cc9ac437991bdb9fb3f4ef1801structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/214c5995524e0b501a490342.xml"},{"id":93188531,"identity":"743c2dff-f857-4b2a-951d-347520dc6650","added_by":"auto","created_at":"2025-10-10 03:35:39","extension":"html","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":102695,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1/088a45507f3aa44c94dae8bf.html"},{"id":93190688,"identity":"d88dc594-608d-4ef0-90cf-5613d22d0243","added_by":"auto","created_at":"2025-10-10 04:07:38","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":598483,"visible":true,"origin":"","legend":"","description":"","filename":"AGNEWSPAPERfinal.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7420392/v1_covered_5a9ff6ed-ffeb-4586-b1af-7e3027e071fc.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"\u003cp\u003eParameter-Efficient Fine-Tuning (PEFT) Approaches for Large Language Models: A Comparative Analysis on AG News\u003c/p\u003e","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":"international-journal-of-networked-and-distributed-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [International Journal of Networked and Distributed Computing](https://link.springer.com/journal/44227)","snPcode":"44227","submissionUrl":"https://submission.springernature.com/new-submission/44227/3","title":"International Journal of Networked and Distributed Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Text Classification, AG News, DistilBERT, LoRA, Parameter-Efficient Fine-Tuning (PEFT), Machine Learning, NLP, TF-IDF, Transformer Models, Model Optimization","lastPublishedDoi":"10.21203/rs.3.rs-7420392/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7420392/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eText classification remains a cornerstone task in Natural Language Processing (NLP), playing a critical role in organizing and understanding large-scale textual data. This study investigates the performance of traditional machine learning algorithms and transformer-based architectures on the AG News dataset, a widely used benchmark for multi-class news classification. In particular, the performance of the DistilBERT model and its Low-Rank Adaptation (LoRA)-enhanced version are examined under a consistent experimental framework that includes different vectorization techniques and parameter configurations. The classical models are evaluated using Count Vectorizer, TF-IDF, Hashing Vectorizer, and semantic embeddings via Word2Vec (CBOW and Skip-gram), while transformer-based models are fine-tuned with varying batch sizes, input lengths, and epochs. The experimental results demonstrate that traditional classifiers, such as Ridge Classifier and Complement Naive Bayes, achieve strong performance when paired with TF-IDF and Count Vectorizer, yielding accuracies exceeding 89% with minimal computational overhead. Meanwhile, the standard DistilBERT model achieved 89.8% accuracy but required over 6 hours of training. By contrast, the LoRA-enhanced DistilBERT attained 90.0% accuracy with a 40% reduction in training time, highlighting the impact of parameter-efficient fine-tuning (PEFT) strategies. These findings underscore the trade-offs between model complexity, computational efficiency, and classification accuracy, and establish LoRA as a practical solution for scalable transformer fine-tuning.\u003c/p\u003e\u003cp\u003e.\u003c/p\u003e","manuscriptTitle":"Parameter-Efficient Fine-Tuning (PEFT) Approaches for Large Language Models: A Comparative Analysis on AG News","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-10 03:35:33","doi":"10.21203/rs.3.rs-7420392/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"decision","content":"Revision requested","date":"2026-04-21T03:22:20+00:00","index":"","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-20T14:05:36+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-10T05:03:42+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"22793707194479322004275196452295069940","date":"2026-04-09T05:38:41+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"169141298649782398302687414225659362938","date":"2026-04-09T02:19:18+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-09-29T08:36:57+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-08-27T13:16:13+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-08-25T15:55:24+00:00","index":"","fulltext":""},{"type":"submitted","content":"International Journal of Networked and Distributed Computing","date":"2025-08-20T19:55:43+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"international-journal-of-networked-and-distributed-computing","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"","sideBox":"Learn more about [International Journal of Networked and Distributed Computing](https://link.springer.com/journal/44227)","snPcode":"44227","submissionUrl":"https://submission.springernature.com/new-submission/44227/3","title":"International Journal of Networked and Distributed Computing","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"stoa","reportingPortfolio":"Springer Open","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"7e90859e-2bfd-4c5f-90fa-b20103afc100","owner":[],"postedDate":"October 10th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"in-revision","subjectAreas":[],"tags":[],"updatedAt":"2026-04-21T03:39:02+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-10 03:35:33","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7420392","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7420392","identity":"rs-7420392","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}