Empirical Evaluation of - LLM Performance Using K-S Test

Empirical Evaluation of - LLM Performance Using K-S Test | 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Research Article Empirical Evaluation of - LLM Performance Using K-S Test Sasikanth Panta This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4674665/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 Research focuses on the novel empirical formulation of large language models which is an interface for scaling down repetitive tasks and back propagating the training dataset from text generation, network hierarchy, associative memory in linguistic dissemination and trained on set of information such as web and scientific literature, feedback score for prompting and building a loss function (Chain of thought) for accurate representation among validators and predictors of the model. This paper focuses on establishing the prompt deterministic function based on knowledge graphs . Models like GPT 4.0, Gemini 1.5 , Llama 2,3 , Anthropic etc. are evaluated using Kolmogorov Smirnov Test which address the bottlenecks of hallucination of prompts in large language models applications. So, Kolmogorov-Smirnov Test, is a non parametric statistical test to evaluate the benchmarks of a large language model application. Top Kolmogorov Tests are different during model training & safety of the model is ensured during benchmark assessment. Artificial Intelligence and Machine Learning Large Language Model Knowledge Graph Deterministic Function Loss Function 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-4674665","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":321758937,"identity":"bf67c121-6006-47b1-8f61-75759515718e","order_by":0,"name":"Sasikanth Panta","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA/ElEQVRIiWNgGAWjYHACA4YEMM3DcIChAkgzMzcQo8UAquUMSAsjEVoYoFoYGNtAAgS0mLc3b/zw4M8fefP+swcPF86rjeZvB2r5UbENpxaZM8eKJRLbDAzn3MhLODxz2/HcGYcZGxh7ztzGqUVCIsdAIrHBgHGGBI/BYd5tx3IbgFqYGdvwaJF/Y/wj4Y+B/Qz+M0Atc47lzieoRYLHTCKBzSBxBkMOUEtDTe4Gglp40sosEtuMk2cAXXh4xrEDuRuBWg7i9Qv74c03f/yRswU6zPhzQU1d7rzzhw8++FGBWwsKYGZgOAxmHCBOPURLHdGKR8EoGAWjYOQAAOK7XA6PnzeQAAAAAElFTkSuQmCC","orcid":"https://orcid.org/0009-0002-0301-5411","institution":"NBKR Institute of Science and Technology","correspondingAuthor":true,"prefix":"","firstName":"Sasikanth","middleName":"","lastName":"Panta","suffix":""}],"badges":[],"createdAt":"2024-07-02 13:42:59","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-4674665/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4674665/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":59951447,"identity":"a73a4fcb-c6c0-4177-91d2-82e6069af0e1","added_by":"auto","created_at":"2024-07-09 17:50:44","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":937896,"visible":true,"origin":"","legend":"","description":"","filename":"EmpiricalEvaluationofLLMPerformanceUsingKSTest.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4674665/v1_covered_76f0618f-0822-4b17-89ac-30e78ddec4ef.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eEmpirical Evaluation of - LLM Performance Using K-S Test\u003c/strong\u003e\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"NBKR Institute of Science and Technology ","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 Model, Knowledge Graph, Deterministic Function, Loss Function","lastPublishedDoi":"10.21203/rs.3.rs-4674665/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4674665/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis Research focuses on the novel empirical formulation of large language models which is an interface for scaling down repetitive tasks and back propagating the training dataset from text generation, network hierarchy, associative memory in linguistic dissemination and \u0026nbsp;trained on set of information such as web and scientific literature, feedback score for prompting and building a loss function (Chain of thought) for accurate representation \u0026nbsp;among validators and predictors of the model. This paper focuses on establishing the prompt deterministic function based on knowledge graphs . Models like GPT 4.0, Gemini 1.5 , Llama 2,3 , Anthropic etc. are evaluated using Kolmogorov Smirnov Test\u003cstrong\u003e \u003c/strong\u003ewhich address the bottlenecks of hallucination of prompts in large language models applications. So, Kolmogorov-Smirnov Test, is a \u003cstrong\u003enon parametric statistical test\u003c/strong\u003e to evaluate the benchmarks of a large language model application. Top Kolmogorov Tests are different during model training \u0026amp; safety of the model is ensured during benchmark assessment.\u003c/p\u003e","manuscriptTitle":"Empirical Evaluation of - LLM Performance Using K-S Test","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-07-09 17:42:36","doi":"10.21203/rs.3.rs-4674665/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":"2350bcf4-d44b-4236-b2f1-e077cf8fff41","owner":[],"postedDate":"July 9th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":34017996,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2024-07-09T17:42:36+00:00","versionOfRecord":[],"versionCreatedAt":"2024-07-09 17:42:36","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4674665","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4674665","identity":"rs-4674665","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}