Data2Dialogue: Structured Enterprise Knowledge Grounding in LLM Agents for Personalized Wellness Sales

Data2Dialogue: Structured Enterprise Knowledge Grounding in LLM Agents for Personalized Wellness Sales | 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 Data2Dialogue: Structured Enterprise Knowledge Grounding in LLM Agents for Personalized Wellness Sales Shijin Wang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6727135/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 Large language models (LLMs) have the potential to revolutionize various domains, including personalized wellness sales, by integrating structured enterprise knowledge into their frameworks. In this context, we introduce Data2Dialogue, a framework designed specifically for enhancing LLMs’ conversational abilities through structured data integration. By leveraging diverse sources of enterprise knowledge, Data2Dialogue enables LLMs to provide tailored product recommendations that cater to individual wellness needs. The approach incorporates advanced knowledge extraction and contextualization techniques to ensure the information delivered is both relevant and responsive to users’ inquiries in real-time. A multi-step inferencing process enhances the LLM’s grasp of enterprise-specific knowledge while improving dialogic engagement. Experimental results indicate that Data2Dialogue leads to higher customer satisfaction and increased sales conversions compared to conventional methods. By grounding LLMs in structured knowledge, the framework fosters more accurate and context-rich interactions, effectively aligning user inquiries with product offerings. Theoretical Computer Science Knowledge Graph LLM Agents Interactive Query 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-6727135","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":460584556,"identity":"6f8602b7-c9fb-4746-975d-a20d01d6fa79","order_by":0,"name":"Shijin Wang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABFElEQVRIie3RMWrDMBSA4ScM7mKS1YZiX0FCYDoEchUZQyaRvVOUxVkCWWs69Art1tFBQxYFrxoyJBRChxTcrQUPlT21YDcZC9U/CCHehwQCsNn+boWHFqLdfD88R5bNBGsW5zIC4LMLCd5s5SvUu2snf1u/3H7swuGqNJtnCAeadRM1ndyg7Oih+2lKFDtSX6cO2SqgQQ+JCx5jJKQhPA4Ek4nQjhvMM0ge+0h5ijHUhuSqJbOHUl59GjLrJZrTPbiG3HktYbhIXWQIwz1krE8xJJkhS06JmEjypFNqHuaTXO07SbDitKpqOSYLRQ5iJKOwXB/e59koGmy6bzG57Y8Q8fPU7xtvcqpmjX4bsdlstv/dF8bAaigaV+NAAAAAAElFTkSuQmCC","orcid":"","institution":"Northeastern University","correspondingAuthor":true,"prefix":"","firstName":"Shijin","middleName":"","lastName":"Wang","suffix":""}],"badges":[],"createdAt":"2025-05-22 17:48:23","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-6727135/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6727135/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":83425984,"identity":"110ab350-1e4b-4bc0-bfde-dfe86d820262","added_by":"auto","created_at":"2025-05-26 04:55:54","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":852334,"visible":true,"origin":"","legend":"","description":"","filename":"9860fb29ac0d47f5825df881b386c219.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6727135/v1_covered_f4e602a8-a5ce-4ced-9ed1-57bd7fcfc07b.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eData2Dialogue: Structured Enterprise Knowledge Grounding in LLM Agents for Personalized Wellness Sales\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Northeastern University","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":"Knowledge Graph, LLM Agents, Interactive Query","lastPublishedDoi":"10.21203/rs.3.rs-6727135/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6727135/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eLarge language models (LLMs) have the potential to revolutionize various domains, including personalized wellness sales, by integrating structured enterprise knowledge into their frameworks. In this context, we introduce Data2Dialogue, a framework designed specifically for enhancing LLMs’ conversational abilities through structured data integration. By leveraging diverse sources of enterprise knowledge, Data2Dialogue enables LLMs to provide tailored product recommendations that cater to individual wellness needs. The approach incorporates advanced knowledge extraction and contextualization techniques to ensure the information delivered is both relevant and responsive to users’ inquiries in real-time. A multi-step inferencing process enhances the LLM’s grasp of enterprise-specific knowledge while improving dialogic engagement. Experimental results indicate that Data2Dialogue leads to higher customer satisfaction and increased sales conversions compared to conventional methods. By grounding LLMs in structured knowledge, the framework fosters more accurate and context-rich interactions, effectively aligning user inquiries with product offerings.\u003c/p\u003e","manuscriptTitle":"Data2Dialogue: Structured Enterprise Knowledge Grounding in LLM Agents for Personalized Wellness Sales","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-05-26 04:47:47","doi":"10.21203/rs.3.rs-6727135/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":"e2aa871d-ef50-47c9-83c2-dd2b6fcca8fd","owner":[],"postedDate":"May 26th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":48926567,"name":"Theoretical Computer Science"}],"tags":[],"updatedAt":"2025-05-26T04:47:47+00:00","versionOfRecord":[],"versionCreatedAt":"2025-05-26 04:47:47","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6727135","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6727135","identity":"rs-6727135","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}