Bring Retrieval Augmented Generation to Google Gemini via External API: An Evaluation with BIG-Bench Dataset

Bring Retrieval Augmented Generation to Google Gemini via External API: An Evaluation with BIG-Bench Dataset | 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 Bring Retrieval Augmented Generation to Google Gemini via External API: An Evaluation with BIG-Bench Dataset Ha-rin Lee, Seo-hyun Kim This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4394715/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 The integration of Retrieval Augmented Generation (RAG) into existing large language models represents a significant shift towards more dynamic and context-aware AI systems. In this work, Google Gemini, a state-of-the-art language model, has been enhanced with RAG capabilities to leverage external, real-time data sources during the response generation process. This augmentation aims to address traditional limitations of language models, particularly in generating responses that require up-to-date information and adaptability to complex user queries. The performance of the RAG-enhanced Google Gemini was rigorously evaluated using the BIG-Bench dataset, which includes tasks designed to test the bounds of language models in terms of reasoning, contextuality, and factual accuracy. Quantitative results from this evaluation demonstrate marked improvements in accuracy and contextual relevance across various tasks, indicating the effectiveness of RAG in enhancing model performance. Qualitative assessments further support these findings, highlighting the model’s improved ability to generate precise and relevant responses. However, the integration of RAG also introduces challenges related to computational efficiency and scalability, emphasizing the need for further optimization. This paper discusses potential future research directions, including the application of RAG to other datasets, exploration of different RAG configurations, and the development of more sophisticated data handling techniques to enhance the model’s performance and applicability. The ongoing advancement of RAG technologies promises to significantly broaden the utility of AI-driven systems in real-world applications, making them more adaptable and useful across diverse and dynamic scenarios. Artificial Intelligence and Machine Learning RAG Gemini benchmarking adaptability scalability 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-4394715","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":300594329,"identity":"669f0712-763e-4bdb-8c7f-c8016482e122","order_by":0,"name":"Ha-rin Lee","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5UlEQVRIiWNgGAWjYBACPgkg8YCBIYGBgbGB4QNIhIGBGa8WNpCWBKgWxhkMDBJsJGgBKuUhSot07wOGhAqbPP7Zh9se21QcrmNjbz5swFBjE41Ti8xxA4aEM2nFEucS241zzhyWYOM5lpzAcCwttwGnw9IYGBLbDic2nGFsk85tA2qRyDE+wNhwmICWf/8T54O0WBKvpeFA4gaQFkaolgSCWhKOJSduBGqR7DmTLtkG9ItBAh6/8IO0fKixS5x3hv2ZxI8Ka35+YIhJfKixwakFCNh/YIol4FY+CkbBKBgFo4AIAADsp1A8+bmMegAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0009-0000-8641-3081","institution":"Chang-ui Gisul Gaebal Senteo","correspondingAuthor":true,"prefix":"","firstName":"Ha-rin","middleName":"","lastName":"Lee","suffix":""},{"id":300594330,"identity":"9bc218c1-cce2-4357-9d1a-8cce40d99538","order_by":1,"name":"Seo-hyun Kim","email":"","orcid":"","institution":"Chang-ui Gisul Gaebal Senteo","correspondingAuthor":false,"prefix":"","firstName":"Seo-hyun","middleName":"","lastName":"Kim","suffix":""}],"badges":[],"createdAt":"2024-05-09 11:06:41","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-4394715/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4394715/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":56214293,"identity":"67d856ec-15ea-4f33-a82b-cee72f9ac294","added_by":"auto","created_at":"2024-05-10 02:28:59","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":238470,"visible":true,"origin":"","legend":"","description":"","filename":"RAG.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4394715/v1_covered_dd8bccc1-d5a3-4e08-8468-11e29c92981b.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eBring Retrieval Augmented Generation to Google Gemini via External API: An Evaluation with BIG-Bench Dataset\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Chang-ui Gisul Gaebal Senteo","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":"RAG, Gemini, benchmarking, adaptability, scalability, AI","lastPublishedDoi":"10.21203/rs.3.rs-4394715/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4394715/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThe integration of Retrieval Augmented Generation (RAG) into existing large language models represents a significant shift towards more dynamic and context-aware AI systems. In this work, Google Gemini, a state-of-the-art language model, has been enhanced with RAG capabilities to leverage external, real-time data sources during the response generation process. This augmentation aims to address traditional limitations of language models, particularly in generating responses that require up-to-date information and adaptability to complex user queries. The performance of the RAG-enhanced Google Gemini was rigorously evaluated using the BIG-Bench dataset, which includes tasks designed to test the bounds of language models in terms of reasoning, contextuality, and factual accuracy. Quantitative results from this evaluation demonstrate marked improvements in accuracy and contextual relevance across various tasks, indicating the effectiveness of RAG in enhancing model performance. Qualitative assessments further support these findings, highlighting the model’s improved ability to generate precise and relevant responses. However, the integration of RAG also introduces challenges related to computational efficiency and scalability, emphasizing the need for further optimization. This paper discusses potential future research directions, including the application of RAG to other datasets, exploration of different RAG configurations, and the development of more sophisticated data handling techniques to enhance the model’s performance and applicability. The ongoing advancement of RAG technologies promises to significantly broaden the utility of AI-driven systems in real-world applications, making them more adaptable and useful across diverse and dynamic scenarios.\u003c/p\u003e","manuscriptTitle":"Bring Retrieval Augmented Generation to Google Gemini via External API: An Evaluation with BIG-Bench Dataset","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-05-10 02:25:31","doi":"10.21203/rs.3.rs-4394715/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":"02702366-8b68-44f7-8fc3-c07f656d893b","owner":[],"postedDate":"May 10th, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":31716491,"name":"Artificial Intelligence and Machine Learning"}],"tags":[],"updatedAt":"2024-05-10T02:25:32+00:00","versionOfRecord":[],"versionCreatedAt":"2024-05-10 02:25:31","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4394715","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4394715","identity":"rs-4394715","version":["v1"]},"buildId":"qtupq5eGEP_6zYnWcrvyt","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}