Improving the Robustness of Large Language Models in Extracting Social Determinants of Health

Improving the Robustness of Large Language Models in Extracting Social Determinants of Health | 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 Improving the Robustness of Large Language Models in Extracting Social Determinants of Health Jiashu Chen, Chase Simmons This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-6255894/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 Accurate extraction of Social Determinants of Health (SDOH) from text is crucial for various healthcare applications. While Large Language Models (LLMs) have shown promise in this domain, their generalization across different datasets remains a challenge. To address this, we propose Iterative Prompt Self-Correction (IPSC), a novel training strategy that enables an LLM to iteratively refine prompts for SDOH extraction through a self-supervised feedback mechanism. Our method utilizes an extraction LLM guided by a set of prompts and an evaluation LLM that assesses the quality of the extracted information. The feedback from the evaluation model is then used to automatically refine the prompts for the subsequent iteration. We evaluated IPSC on two distinct datasets, an SDOH corpus and the MIMIC-III clinical database, and compared its performance against several baseline methods, including standard fine-tuning and basic prompt tuning. Both quantitative results, measured by Precision, Recall, and F1-score, and qualitative human evaluations demonstrate that IPSC significantly outperforms the baselines, leading to more accurate and robust SDOH extraction. Our findings highlight the potential of self-supervised prompt optimization for enhancing the universality of LLMs in specialized information extraction tasks. Social Determinants of Health Large Language Models 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-6255894","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":430676848,"identity":"ceea33df-8441-4918-9328-5bd5f46a4f43","order_by":0,"name":"Jiashu Chen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA8ElEQVRIiWNgGAWjYBACNvbmgw8SKmzk7NsbEKIS+LTw8RxLNvhwJs3YgOcAkVrkJHLMJGe2HU7cIJFApBY2oBZp3rbDjNslXyd/YGzbZi/fwHzwNg8+LTzPiq15zqUzW87O3SbB2HY7ccMBtmRrvFrYkzfe5imzZmO4nbuNAaglwYCBx0warxaGBANpHjZmHoabZzcDHXYb6DD+b/i1cKQYSc5oc5YwuMG7AeQwxoYDPGz4tUAD2UCyB+iXhHNAvxxmM7acg0eLfDskKuv72YEO+1AGdFh788Mbb/BoQQUJIIKZaOWjYBSMglEwCnABAOchTh6nwsS/AAAAAElFTkSuQmCC","orcid":"","institution":"Idaho State University","correspondingAuthor":true,"prefix":"","firstName":"Jiashu","middleName":"","lastName":"Chen","suffix":""},{"id":430676849,"identity":"e82835c5-e8f6-45f5-af96-574211b06e7f","order_by":1,"name":"Chase Simmons","email":"","orcid":"","institution":"Idaho State University","correspondingAuthor":false,"prefix":"","firstName":"Chase","middleName":"","lastName":"Simmons","suffix":""}],"badges":[],"createdAt":"2025-03-18 19:36:51","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-6255894/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-6255894/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":79065337,"identity":"7a491e75-01d2-46aa-b690-57771912f2ed","added_by":"auto","created_at":"2025-03-24 04:07:37","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":216645,"visible":true,"origin":"","legend":"","description":"","filename":"Determinants.pdf","url":"https://assets-eu.researchsquare.com/files/rs-6255894/v1_covered_d497b03f-a7a3-4240-84b4-dacfd2ec22a8.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003eImproving the Robustness of Large Language Models in Extracting Social Determinants of Health\u003c/p\u003e","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"Idaho State 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":"Social Determinants of Health, Large Language Models","lastPublishedDoi":"10.21203/rs.3.rs-6255894/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-6255894/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eAccurate extraction of Social Determinants of Health (SDOH) from text is crucial for various healthcare applications. While Large Language Models (LLMs) have shown promise in this domain, their generalization across different datasets remains a challenge. To address this, we propose Iterative Prompt Self-Correction (IPSC), a novel training strategy that enables an LLM to iteratively refine prompts for SDOH extraction through a self-supervised feedback mechanism. Our method utilizes an extraction LLM guided by a set of prompts and an evaluation LLM that assesses the quality of the extracted information. The feedback from the evaluation model is then used to automatically refine the prompts for the subsequent iteration. We evaluated IPSC on two distinct datasets, an SDOH corpus and the MIMIC-III clinical database, and compared its performance against several baseline methods, including standard fine-tuning and basic prompt tuning. Both quantitative results, measured by Precision, Recall, and F1-score, and qualitative human evaluations demonstrate that IPSC significantly outperforms the baselines, leading to more accurate and robust SDOH extraction. Our findings highlight the potential of self-supervised prompt optimization for enhancing the universality of LLMs in specialized information extraction tasks.\u003c/p\u003e","manuscriptTitle":"Improving the Robustness of Large Language Models in Extracting Social Determinants of Health","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-03-24 03:59:30","doi":"10.21203/rs.3.rs-6255894/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":"2bc5eeb9-2fdb-4b9b-82fe-7ab85fc0b2d4","owner":[],"postedDate":"March 24th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-03-24T03:59:30+00:00","versionOfRecord":[],"versionCreatedAt":"2025-03-24 03:59:30","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-6255894","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-6255894","identity":"rs-6255894","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}