Tuning LLaMA Model with Mental Disorders Knowledge

Tuning LLaMA Model with Mental Disorders Knowledge | 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Article Tuning LLaMA Model with Mental Disorders Knowledge Xiujie Zhao, Yu Gao, Yimeng Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-4250151/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 shown its strong emergent ability in many general domain and can achieve good results in natural language processing (NLP) tasks. However, LLMs have not yet shown promising ability in the medical field, especially in the diagnosis of mental disorders, due to the protection of patients' private information and the limitation of psychological terminology. To this end, we collected nearly 7000 real medical records of various mental disorders from a specialized hospital and used them as instruction after data cleansing and manual proofreading for psychological field. We proposed the model named “ZhiXin”, a LLaMA-based model that has been fine-tuned with our own instruction. The experimental results show that our model outperforms the state-of-the-art approaches in terms of mental disorders diagnosis. In the meanwhile, our model also ensures the Safety, Usability and Smoothness of the response which is closer to the answer of a psychiatrist during the diagnosis of mental disorders. Thus ZinXin model can help patients and families with intelligent assisted diagnosis and reduce the workload of psychologists. Health sciences/Health care Physical sciences/Engineering Large Language Models Mental Disorders Instruction Fine-tuning Intelligent Diagnostics Full Text Additional Declarations No competing interests reported. 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-4250151","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":293242226,"identity":"5ae78d0d-b2c7-4594-9299-daa84d862ae2","order_by":0,"name":"Xiujie Zhao","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBUlEQVRIiWNgGAWjYDACCRBhwMDMxsB8ACzA3gAkeIjTwpYAFuA5RpQWiFoD4rTIz25++Jin4DA7H3vPtwcf2+rkeOQbGB+8bWOQN8ehhXHOMWPDGQaHmdl4zm43nNl22JgH6CvDuW0MhjsbsGthlkgwk/gA0iKRu02at+1A4n6gr4AMhgSDA9i1sEmkf5NIAGmRf/NM+m9bXWIPGwP7b3xaeCRyYLbwsEkztjGDtLAx49MiIZFTDPRLOtAvaWaSPedAfklslpxzTsJwAw4t8jPSNz7m+WOdLN9++JnEjzJgiDEfPvjhTZmNPC5bYCAZic3YwIAcX7iAHUEVo2AUjIJRMHIBAOfETVtt2JFWAAAAAElFTkSuQmCC","orcid":"","institution":"Dalian Neusoft University of Information","correspondingAuthor":true,"prefix":"","firstName":"Xiujie","middleName":"","lastName":"Zhao","suffix":""},{"id":293242227,"identity":"9b1bc8c7-7326-466f-bc4b-25eb61b7025b","order_by":1,"name":"Yu Gao","email":"","orcid":"","institution":"Dalian Cuike Software Information Technology Service Co., LTD","correspondingAuthor":false,"prefix":"","firstName":"Yu","middleName":"","lastName":"Gao","suffix":""},{"id":293242228,"identity":"5b21ec14-f648-4076-b1b3-465804c215e7","order_by":2,"name":"Yimeng Zhang","email":"","orcid":"","institution":"Dalian Neusoft University of Information","correspondingAuthor":false,"prefix":"","firstName":"Yimeng","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2024-04-11 04:14:22","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-4250151/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-4250151/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":59822798,"identity":"39321179-73ec-4a58-bcfe-4bddb419515d","added_by":"auto","created_at":"2024-07-08 04:38:39","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":627550,"visible":true,"origin":"","legend":"","description":"","filename":"TuningLLaMAModelwithMentalDisordersKnowledge.pdf","url":"https://assets-eu.researchsquare.com/files/rs-4250151/v1_covered_586efc61-2d79-4341-9a2f-0eb336a43416.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Tuning LLaMA Model with Mental Disorders Knowledge","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"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":"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 Models, Mental Disorders, Instruction Fine-tuning, Intelligent Diagnostics","lastPublishedDoi":"10.21203/rs.3.rs-4250151/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-4250151/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":" Large Language Models (LLMs) have shown its strong emergent ability in many general domain and can achieve good results in natural language processing (NLP) tasks. However, LLMs have not yet shown promising ability in the medical field, especially in the diagnosis of mental disorders, due to the protection of patients' private information and the limitation of psychological terminology. To this end, we collected nearly 7000 real medical records of various mental disorders from a specialized hospital and used them as instruction after data cleansing and manual proofreading for psychological field. We proposed the model named “ZhiXin”, a LLaMA-based model that has been fine-tuned with our own instruction. The experimental results show that our model outperforms the state-of-the-art approaches in terms of mental disorders diagnosis. In the meanwhile, our model also ensures the Safety, Usability and Smoothness of the response which is closer to the answer of a psychiatrist during the diagnosis of mental disorders. Thus ZinXin model can help patients and families with intelligent assisted diagnosis and reduce the workload of psychologists.","manuscriptTitle":"Tuning LLaMA Model with Mental Disorders Knowledge","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2024-04-22 06:06:21","doi":"10.21203/rs.3.rs-4250151/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":"97f640c6-94c9-4040-83c6-d451c127891a","owner":[],"postedDate":"April 22nd, 2024","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":30907822,"name":"Health sciences/Health care"},{"id":30907823,"name":"Physical sciences/Engineering"}],"tags":[],"updatedAt":"2024-12-12T01:38:16+00:00","versionOfRecord":[],"versionCreatedAt":"2024-04-22 06:06:21","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-4250151","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-4250151","identity":"rs-4250151","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}