Harmfulness analysis of Large Language Model answers to dental questions

preprint OA: closed
Full text JSON View at publisher
AI-generated deep summary by claude@2026-06, 2026-06-24 · read from full text

This preprint evaluates the safety of Large Language Model (LLM) responses to dental questions by creating a set of 30 questions based on the experience of practicing dentists. Model answers were categorized by two independent dentists with 5 years of practice experience using assessments of safety and information reliability, respectively. The authors report that currently available models are not fully safe for dental patients, attributing this to patients’ frequent seeking of solutions for dental problems and patients’ lack of advanced medical knowledge. The paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Full text 10,530 characters · extracted from preprint-html · click to expand
Harmfulness analysis of Large Language Model answers to dental questions | 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 Harmfulness analysis of Large Language Model answers to dental questions Martyna Mysior, Marek Piotr Mysior, Pamela Maslowski, Katarzyna Skośkiewicz-Malinowska This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7456616/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 It became common for patients to use the Internet as a source of solutions to medical questions, including dental problems. Furthermore, the use of Large Language Models has recently become widely available to the public. The aim of this study was to assess the safety of patients in the aspect of using Large Language Models to answer dental questions. Based on the experience of practicing dentists, a set of 30 questions was created. The models' responses were categorized by two independent dentists with 5 years of practice experience into categories evaluating safety and information reliability. It was shown that currently available models are not fully safe for dental patients. The frequent search for solutions to their dental problems and the lack of advanced medical knowledge among patients generate the need to create a safe place for patients on the web. Health sciences/Health care Health sciences/Medical research Full Text Additional Declarations No competing interests reported. Supplementary Files SciRepsupplement.pdf 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-7456616","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Article","associatedPublications":[],"authors":[{"id":570368720,"identity":"f9db337c-0703-4aed-a5d3-91675b67fa4d","order_by":0,"name":"Martyna Mysior","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA30lEQVRIiWNgGAWjYDADNgYGxgdAmoePCMWMDVAtzAYgLWxEawHpkoDqxQ90288+f8CYc9iej733WeXXHDsZNgbmh49u4NFidibdsIFx2+HENp7jZrdltyUDHcZmbJyDT8uBNEaQlgQ2iTS225LbmIFaeNik8Wo5/wysxR6kpVhyWz0RWm5AbGFsA2ph/LjtMDFanjHOSNyWDvTLMWZpxm3HediYCfnlfBrDh4/brO3l29sYP/7cVm3Pz9788DE+LWCQwNAMppl5wCQh5RBQByYZfxCnehSMglEwCkYYAAA8GUHShPwTkwAAAABJRU5ErkJggg==","orcid":"","institution":"SCTT Academic Dental Polyclinic","correspondingAuthor":true,"prefix":"","firstName":"Martyna","middleName":"","lastName":"Mysior","suffix":""},{"id":570368721,"identity":"e6c0fd11-1298-4f27-9958-bb8046046fc3","order_by":1,"name":"Marek Piotr Mysior","email":"","orcid":"","institution":"Wrocław University of Science and Technology","correspondingAuthor":false,"prefix":"","firstName":"Marek","middleName":"Piotr","lastName":"Mysior","suffix":""},{"id":570368722,"identity":"c8bd02cf-be9a-466f-aa38-727eea98d6c0","order_by":2,"name":"Pamela Maslowski","email":"","orcid":"","institution":"Wroclaw Medical University","correspondingAuthor":false,"prefix":"","firstName":"Pamela","middleName":"","lastName":"Maslowski","suffix":""},{"id":570368723,"identity":"e41bde28-a94a-472c-8a75-a48582933780","order_by":3,"name":"Katarzyna Skośkiewicz-Malinowska","email":"","orcid":"","institution":"Wroclaw Medical University","correspondingAuthor":false,"prefix":"","firstName":"Katarzyna","middleName":"","lastName":"Skośkiewicz-Malinowska","suffix":""}],"badges":[],"createdAt":"2025-08-25 19:38:09","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7456616/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7456616/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":100000655,"identity":"3d7613d7-8f62-44ab-ae2d-13ed0771bbf1","added_by":"auto","created_at":"2026-01-12 04:32:10","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":5542,"visible":true,"origin":"","legend":"","description":"","filename":"ed770f1fafd44f36a6cbd373aba39cac.json","url":"https://assets-eu.researchsquare.com/files/rs-7456616/v1/3dbcc3813bcb943680e5c7c0.json"},{"id":102383500,"identity":"5d5aab8f-0dce-41c8-b666-d4a19872f9f1","added_by":"auto","created_at":"2026-02-11 07:13:27","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1501099,"visible":true,"origin":"","legend":"","description":"","filename":"SciRepsubmission3.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7456616/v1_covered_354ada59-d0b6-4ed8-bfc8-264016b49cd5.pdf"},{"id":100000654,"identity":"ca5d5013-6e01-41b3-adf1-0c81f214e001","added_by":"auto","created_at":"2026-01-12 04:32:10","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":203459,"visible":true,"origin":"","legend":"","description":"","filename":"SciRepsupplement.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7456616/v1/a65419ba697eeb775140a23e.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Harmfulness analysis of Large Language Model answers to dental questions","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":"","lastPublishedDoi":"10.21203/rs.3.rs-7456616/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7456616/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"It became common for patients to use the Internet as a source of solutions to medical questions, including dental problems. Furthermore, the use of Large Language Models has recently become widely available to the public. The aim of this study was to assess the safety of patients in the aspect of using Large Language Models to answer dental questions. Based on the experience of practicing dentists, a set of 30 questions was created. The models' responses were categorized by two independent dentists with 5 years of practice experience into categories evaluating safety and information reliability. It was shown that currently available models are not fully safe for dental patients. The frequent search for solutions to their dental problems and the lack of advanced medical knowledge among patients generate the need to create a safe place for patients on the web.","manuscriptTitle":"Harmfulness analysis of Large Language Model answers to dental questions","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-01-12 04:32:03","doi":"10.21203/rs.3.rs-7456616/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":"10aa7df7-ff75-4d04-8ccf-525b66a56046","owner":[],"postedDate":"January 12th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":60692956,"name":"Health sciences/Health care"},{"id":60692957,"name":"Health sciences/Medical research"}],"tags":[],"updatedAt":"2026-02-11T07:11:54+00:00","versionOfRecord":[],"versionCreatedAt":"2026-01-12 04:32:03","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7456616","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7456616","identity":"rs-7456616","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2026) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00