Efficiency in Language Understanding and Generation: An Evaluation of Four Open-Source Large Language Models

preprint OA: closed CC-BY-4.0
📄 Open PDF Full text JSON View at publisher
Full text 10,297 characters · extracted from preprint-html · click to expand
Efficiency in Language Understanding and Generation: An Evaluation of Four Open-Source 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 Efficiency in Language Understanding and Generation: An Evaluation of Four Open-Source Large Language Models Siu Ming Wong, Ho Leung, Ka Yan Wong This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4063228/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 This study provides a comprehensive evaluation of the efficiency of Large Language Models (LLMs) in performing diverse language understanding and generation tasks. Through a systematic comparison of open-source models including GPT-Neo, Bloom, FLAN-T5, and Mistral-7B, the research explores their performance across widely recognized benchmarks such as GLUE, SuperGLUE, LAMBADA, and SQuAD. Our findings reveal significant variations in model accuracy, computational efficiency, scalability, and adaptability, underscoring the influence of model architecture and training paradigms on performance outcomes. The study identifies key factors contributing to the models' efficiency and offers insights into potential optimization strategies for enhancing their applicability in real-world NLP applications. By highlighting the strengths and limitations of current LLMs, this research contributes to the ongoing development of more effective, efficient, and adaptable language models, paving the way for future advancements in the field of natural language processing. Artificial Intelligence and Machine Learning Large Language Models Natural Language Processing Model Efficiency Computational Efficiency Scalability Adaptability 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-4063228","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":277849172,"identity":"2fc926e9-3619-4748-aa28-671b62479542","order_by":0,"name":"Siu Ming Wong","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABE0lEQVRIiWNgGAWjYBCDBAkGxsYHHwxsEiDcAqK0MDcbzqhIS2BgA3ENiNLC3ibNc+YwRAsDHi3y084YPi74xZAn2cDYJs3bdj6PX7478cMDAwZ5frEDWLUY3M4xNp7Zx1AszcDYbDm37XaxZBvvZgmgwwxnzk7ArkU6d5s0bw9D4jyg92+8bbuduOEY7waQlgSD29i1yM9GaGmQ4G07B9Ky+Qc+LQy3gVp4fjAkzmZgbJLkOXMApGUbXlsMbud/NuZtYEic2cAICuTkxJltudssEgwkcPpFfnZa4mOePwyJMw6wPwRGpV1iP/PZzTd/VNjI80vjcBgIMLb9B2p+gCImgVs5GPwhID8KRsEoGAUjGwAAtuZhrwEL0FcAAAAASUVORK5CYII=","orcid":"https://orcid.org/0009-0003-7291-6261","institution":"","correspondingAuthor":true,"prefix":"","firstName":"Siu","middleName":"Ming","lastName":"Wong","suffix":""},{"id":277849173,"identity":"c06167a2-e770-46bd-9925-90a84ae381c1","order_by":1,"name":"Ho Leung","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Ho","middleName":"","lastName":"Leung","suffix":""},{"id":277849174,"identity":"e9a22119-a753-44a2-b3d5-4e52d59db936","order_by":2,"name":"Ka Yan Wong","email":"","orcid":"","institution":"","correspondingAuthor":false,"prefix":"","firstName":"Ka","middleName":"Yan","lastName":"Wong","suffix":""}],"badges":[],"createdAt":"2024-03-10 08:42:18","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-4063228/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4063228/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":52397285,"identity":"794edfe3-89e5-4c0a-9ab2-90902b6fc847","added_by":"auto","created_at":"2024-03-11 05:43:22","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":186364,"visible":true,"origin":"","legend":"","description":"","filename":"smw.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4063228/v1_covered_c9d874ce-2b06-41ed-aac8-fbda3c333399.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eEfficiency in Language Understanding and Generation: An Evaluation of Four Open-Source 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, Natural Language Processing, Model Efficiency, Computational Efficiency, Scalability, Adaptability","lastPublishedDoi":"10.21203/rs.3.rs-4063228/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4063228/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study provides a comprehensive evaluation of the efficiency of Large Language Models (LLMs) in performing diverse language understanding and generation tasks. Through a systematic comparison of open-source models including GPT-Neo, Bloom, FLAN-T5, and Mistral-7B, the research explores their performance across widely recognized benchmarks such as GLUE, SuperGLUE, LAMBADA, and SQuAD. Our findings reveal significant variations in model accuracy, computational efficiency, scalability, and adaptability, underscoring the influence of model architecture and training paradigms on performance outcomes. The study identifies key factors contributing to the models' efficiency and offers insights into potential optimization strategies for enhancing their applicability in real-world NLP applications. By highlighting the strengths and limitations of current LLMs, this research contributes to the ongoing development of more effective, efficient, and adaptable language models, paving the way for future advancements in the field of natural language processing.\u003c/p\u003e","manuscriptTitle":"Efficiency in Language Understanding and Generation: An Evaluation of Four Open-Source Large Language Models","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-03-11 05:35:13","doi":"10.21203/rs.3.rs-4063228/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":"f01d4f6c-d7a4-4d8b-b0d7-fc5556c66758","owner":[],"postedDate":"March 11th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":29271420,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2024-03-11T05:35:13+00:00","versionOfRecord":[],"versionCreatedAt":"2024-03-11 05:35:13","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4063228","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4063228","identity":"rs-4063228","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2024) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00
unpaywall
last seen: 2026-05-23T02:00:01.238055+00:00
License: CC-BY-4.0