Reinforcement Learning for the Computational Interpretation of Classical Medical Heritage Texts

Reinforcement Learning for the Computational Interpretation of Classical Medical Heritage Texts | 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 Article Reinforcement Learning for the Computational Interpretation of Classical Medical Heritage Texts Si Xie, Wei Liu, Jueling Luo, Xiyue Song, Mei Ouyang, Wanjin Song, and 1 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9067668/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Traditional Chinese Medicine (TCM) classics are a major form of intangible heritage, preserving historically layered medical knowledge, diagnostic logic, and therapeutic epistemologies. For heritage-text digitisation, interpretive fidelity and epistemological continuity are as critical as linguistic fluency. We present R1-TCM-Translator, a heritage-oriented framework for ancient-to-modern Chinese medical translation that combines multi-objective reinforcement learning (GRPO) with a structured six-step reasoning process to make cultural-epistemic reconstruction explicit and auditable. Experiments on a philologically curated parallel corpus of 15,387 sentence pairs from eight representative TCM classics show consistent improvements over supervised fine-tuning baselines and strong general-purpose large models. R1-TCM-Translator-8B demonstrates consistent gains on lexical-alignment and semantic-consistency metrics, specifically BLEU and COMET, indicating improved cross-text interpretive stability rather than metric-specific optimisation alone. Fine-grained analyses further show an approximately 23-percentage-point increase in specialised terminology accuracy and improved consistency in interpreting complex pathogenesis-related semantics. These findings suggest that reward-guided structured reasoning can improve epistemic fidelity in digitised medical heritage archives beyond surface-form translation quality. By embedding semantic-fidelity objectives directly into optimisation, the framework operationalises heritage-aware translation as an auditable alignment process rather than a purely generative task. While doctrine-dense passages and composite interpretive risks remain challenging, the framework provides a reproducible computational pathway for digital preservation, knowledge modelling, and digital-humanities research on medical heritage texts. Traditional Chinese Medicine classics Intangible cultural heritage Heritage text translation Reinforcement learning Epistemic fidelity Digital humanities Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 18 Apr, 2026 Reviews received at journal 06 Apr, 2026 Reviewers agreed at journal 16 Mar, 2026 Reviewers invited by journal 15 Mar, 2026 Editor assigned by journal 12 Mar, 2026 Submission checks completed at journal 12 Mar, 2026 First submitted to journal 08 Mar, 2026 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-9067668","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":607189108,"identity":"52cf3890-673a-438e-bc4b-1a7a1f2ec4b6","order_by":0,"name":"Si Xie","email":"","orcid":"","institution":"Hunan University of Traditional Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Si","middleName":"","lastName":"Xie","suffix":""},{"id":607189109,"identity":"e1eecdf2-11a1-4a35-bba5-621178076a5d","order_by":1,"name":"Wei Liu","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAAyElEQVRIiWNgGAWjYFACxsYDCQw2CVAeM1FaGoBa0kjSwsBwgIHhMAlaDI43Nxx42HY+z1wi+ekGhgrrxAb2swfwazlzsOFAYtvtYssZaWY3GM6kJzbw5CXg1WJ2IxGsJXHDjRy2G4xthxMbJHgM8Gu5/xCk5RxUyz9itNxgBGk5ANXSQIQW+zNAhyWcS07ccOaZ2Y2EY+nGbTw5+LVIth9/+PBHmV3ihuPJz258qLGW7Wc/g18LKkgAYjYS1I+CUTAKRsEowAEAL0JSJFtwhdoAAAAASUVORK5CYII=","orcid":"","institution":"Hunan University of Traditional Chinese Medicine","correspondingAuthor":true,"prefix":"","firstName":"Wei","middleName":"","lastName":"Liu","suffix":""},{"id":607189110,"identity":"3135508f-8b06-491c-bee4-870cee5f134d","order_by":2,"name":"Jueling Luo","email":"","orcid":"","institution":"Changsha Aotu Pigai Intelligent Technology Co., Ltd.","correspondingAuthor":false,"prefix":"","firstName":"Jueling","middleName":"","lastName":"Luo","suffix":""},{"id":607189111,"identity":"2c2e318b-a6ea-4df1-ac29-c423ab6c17c2","order_by":3,"name":"Xiyue Song","email":"","orcid":"","institution":"Hunan University of Traditional Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Xiyue","middleName":"","lastName":"Song","suffix":""},{"id":607189112,"identity":"b9b44d7e-2e00-4dfb-b4a7-8b8716d479d1","order_by":4,"name":"Mei Ouyang","email":"","orcid":"","institution":"Hunan University of Traditional Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Mei","middleName":"","lastName":"Ouyang","suffix":""},{"id":607189113,"identity":"efe0487c-031c-4b3f-92e9-f63255e4ff27","order_by":5,"name":"Wanjin Song","email":"","orcid":"","institution":"Hunan University of Traditional Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Wanjin","middleName":"","lastName":"Song","suffix":""},{"id":607189114,"identity":"7fcb9757-8dc6-44ba-81cc-976007ae9d97","order_by":6,"name":"Wei Hu","email":"","orcid":"","institution":"Hunan University of Traditional Chinese Medicine","correspondingAuthor":false,"prefix":"","firstName":"Wei","middleName":"","lastName":"Hu","suffix":""}],"badges":[],"createdAt":"2026-03-09 02:54:14","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-9067668/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9067668/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104788631,"identity":"dfff808d-40bf-4817-a6da-10c5cf3a4827","added_by":"auto","created_at":"2026-03-17 08:25:21","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1000770,"visible":true,"origin":"","legend":"","description":"","filename":"R1TCMmanuscriptsubmission.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9067668/v1_covered_9dc8ed2b-3783-4487-9f69-10f4b151adde.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Reinforcement Learning for the Computational Interpretation of Classical Medical Heritage Texts","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"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":"npj-heritage-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"hsci","sideBox":"Learn more about [Heritage Science](http://heritagesciencejournal.springeropen.com)","snPcode":"40494","submissionUrl":"https://submission.nature.com/new-submission/40494/3","title":"npj Heritage Science","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true},"keywords":"Traditional Chinese Medicine classics, Intangible cultural heritage, Heritage text translation, Reinforcement learning, Epistemic fidelity, Digital humanities","lastPublishedDoi":"10.21203/rs.3.rs-9067668/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9067668/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"Traditional Chinese Medicine (TCM) classics are a major form of intangible heritage, preserving historically layered medical knowledge, diagnostic logic, and therapeutic epistemologies. For heritage-text digitisation, interpretive fidelity and epistemological continuity are as critical as linguistic fluency. We present R1-TCM-Translator, a heritage-oriented framework for ancient-to-modern Chinese medical translation that combines multi-objective reinforcement learning (GRPO) with a structured six-step reasoning process to make cultural-epistemic reconstruction explicit and auditable. Experiments on a philologically curated parallel corpus of 15,387 sentence pairs from eight representative TCM classics show consistent improvements over supervised fine-tuning baselines and strong general-purpose large models. R1-TCM-Translator-8B demonstrates consistent gains on lexical-alignment and semantic-consistency metrics, specifically BLEU and COMET, indicating improved cross-text interpretive stability rather than metric-specific optimisation alone. Fine-grained analyses further show an approximately 23-percentage-point increase in specialised terminology accuracy and improved consistency in interpreting complex pathogenesis-related semantics. These findings suggest that reward-guided structured reasoning can improve epistemic fidelity in digitised medical heritage archives beyond surface-form translation quality. By embedding semantic-fidelity objectives directly into optimisation, the framework operationalises heritage-aware translation as an auditable alignment process rather than a purely generative task. While doctrine-dense passages and composite interpretive risks remain challenging, the framework provides a reproducible computational pathway for digital preservation, knowledge modelling, and digital-humanities research on medical heritage texts.\n","manuscriptTitle":"Reinforcement Learning for the Computational Interpretation of Classical Medical Heritage Texts","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-17 08:02:40","doi":"10.21203/rs.3.rs-9067668/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"80814344329812486678849834279602698214","date":"2026-04-18T18:16:41+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-04-06T16:49:24+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"196644175729031051875832089784373625552","date":"2026-03-16T11:18:08+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2026-03-16T03:26:22+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2026-03-12T04:25:17+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2026-03-12T04:24:31+00:00","index":"","fulltext":""},{"type":"submitted","content":"npj Heritage Science","date":"2026-03-09T02:50:55+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"npj-heritage-science","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"hsci","sideBox":"Learn more about [Heritage Science](http://heritagesciencejournal.springeropen.com)","snPcode":"40494","submissionUrl":"https://submission.nature.com/new-submission/40494/3","title":"npj Heritage Science","twitterHandle":"@SpringerOpen","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"BMC/SO AJ","inReviewEnabled":true,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"fed9b44a-9dc1-4f1d-85db-33a285dc491d","owner":[],"postedDate":"March 17th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2026-03-17T08:02:40+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-17 08:02:40","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9067668","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9067668","identity":"rs-9067668","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}