{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T10:05:12Z","timestamp":1783937112779,"version":"3.55.0"},"reference-count":25,"publisher":"MDPI AG","issue":"7","license":[{"start":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T00:00:00Z","timestamp":1783036800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Vaccines"],"abstract":"<jats:p>Background\/Objectives: Large language models (LLMs) are increasingly used by the public to seek health information, yet their accuracy in addressing common vaccine myths remains unclear. Sycophantic LLM behavior, where models align with rather than correct user-stated beliefs, poses specific risks in health contexts. Methods: We conducted an exploratory multi-vendor evaluation of three LLMs (GPT-5, Gemini 2.5 Flash, Claude Sonnet 4) using officially curated vaccination myths from Germany\u2019s public health institution and two realistic user framings (curious skeptic, convinced believer). All model responses were independently evaluated by two blinded medical experts for misconception addressal (binary criterion applied to the response text), scientific accuracy, and communication clarity (5-point Likert scales). Additionally, blinded marketing experts ranked models for lay communication clarity. Flesch Reading Ease scores were computed for all outputs. Results: Across all myths, framings, and models (66 response items), both medical raters judged that all responses refuted the targeted misconception; no response affirmed or ignored a myth, including under the adversarial convinced believer framing. Scientific accuracy and clarity ratings were high and tightly clustered (median 4.0\u20134.5), with no combined score below 3 and substantial inter-rater agreement. Marketing experts independently ranked Gemini 2.5 Flash and GPT-5 highest for lay clarity. Readability analysis revealed generally low accessibility, particularly for the convinced believer framing and for Claude Sonnet 4 outputs. Conclusions: Our findings suggest that general-purpose LLMs can produce scientifically accurate, on-topic rebuttals to widely documented vaccine myths under realistic default conditions, although linguistic complexity and framing-sensitive style may limit accessibility. Whether such outputs change beliefs or behavior in hesitant individuals was not tested. With readability optimization, these outputs could serve as building blocks for myth-debunking tools, given prospective evaluation with behavioral endpoints.<\/jats:p>","DOI":"10.3390\/vaccines14070594","type":"journal-article","created":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T15:15:04Z","timestamp":1783091704000},"page":"594","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Leveraging Large Language Models to Address Common Vaccination Myths and Misconceptions"],"prefix":"10.3390","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1064-9173","authenticated-orcid":false,"given":"Florian","family":"Reis","sequence":"first","affiliation":[{"name":"Medical Affairs, Pfizer Pharma GmbH, 10117 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lea J.","family":"Bayer","sequence":"additional","affiliation":[{"name":"Medical Affairs, Pfizer Pharma GmbH, 10117 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudius","family":"Malerczyk","sequence":"additional","affiliation":[{"name":"Medical Affairs, Pfizer Pharma GmbH, 10117 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Lenz","sequence":"additional","affiliation":[{"name":"Medical Affairs, Pfizer Pharma GmbH, 10117 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7821-2359","authenticated-orcid":false,"given":"Christof","family":"von Eiff","sequence":"additional","affiliation":[{"name":"Medical Affairs, Pfizer Pharma GmbH, 10117 Berlin, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,7,3]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"140","DOI":"10.2471\/BLT.07.040089","article-title":"Vaccination greatly reduces disease, disability, death and inequity worldwide","volume":"86","author":"Andre","year":"2008","journal-title":"Bull. World Health Organ."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"4031","DOI":"10.1073\/pnas.1704507114","article-title":"Simply put: Vaccination saves lives","volume":"114","author":"Orenstein","year":"2017","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"e004206","DOI":"10.1136\/bmjgh-2020-004206","article-title":"Social media and vaccine hesitancy","volume":"5","author":"Wilson","year":"2020","journal-title":"BMJ Glob. Health"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"3727","DOI":"10.1016\/j.vaccine.2012.02.025","article-title":"Opportunities and challenges of Web 2.0 for vaccination decisions","volume":"30","author":"Betsch","year":"2012","journal-title":"Vaccine"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1763","DOI":"10.4161\/hv.24657","article-title":"Vaccine hesitancy: An overview","volume":"9","author":"Laberge","year":"2013","journal-title":"Hum. Vaccines Immunother."},{"key":"ref_6","unstructured":"WHO (2025, July 01). Ten Threats to Global Health in 2019. Available online: https:\/\/www.who.int\/news-room\/spotlight\/ten-threats-to-global-health-in-2019."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1038\/s41591-023-02448-8","article-title":"Large language models in medicine","volume":"29","author":"Thirunavukarasu","year":"2023","journal-title":"Nat. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"120","DOI":"10.1038\/s41746-023-00873-0","article-title":"The imperative for regulatory oversight of large language models (or generative AI) in healthcare","volume":"6","author":"Topol","year":"2023","journal-title":"npj Digit. Med."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"e076542","DOI":"10.1136\/bmj-2023-076542","article-title":"Behavioural interventions to reduce vaccine hesitancy driven by misinformation on social media","volume":"384","author":"Ruggeri","year":"2024","journal-title":"BMJ"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1233","DOI":"10.1056\/NEJMsr2214184","article-title":"Benefits, Limits, and Risks of GPT-4 as an AI Chatbot for Medicine","volume":"388","author":"Lee","year":"2023","journal-title":"N. Engl. J. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"446","DOI":"10.1007\/s10439-023-03305-y","article-title":"ChatGPT and Vaccines: Can AI Chatbots Boost Awareness and Uptake?","volume":"52","author":"Sohail","year":"2023","journal-title":"Ann. Biomed. Eng."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"e60939","DOI":"10.2196\/60939","article-title":"Ensuring Accuracy and Equity in Vaccination Information From ChatGPT and CDC: Mixed-Methods Cross-Language Evaluation","volume":"8","author":"Joshi","year":"2024","journal-title":"JMIR Form. Res."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Koh, M.C.Y., Ngiam, J.N., Salada, B.M.A., Tambyah, P.A., Archuleta, S., and Oon, J.E.L. (2025). Can ChatGPT Counter Vaccine Hesitancy? An Evaluation of ChatGPT\u2019s Responses to Simulated Queries from the General Public. Healthcare, 13.","DOI":"10.3390\/healthcare13111269"},{"key":"ref_14","unstructured":"RKI (2025, July 01). Vaccination Myths: Effectively Debunking Misinformation. Available online: https:\/\/www.rki.de\/EN\/Topics\/Infectious-diseases\/Immunisation\/Information-material\/Vaccination-myths\/effectively-debunking-misinformation-node.html."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"14604582231169297","DOI":"10.1177\/14604582231169297","article-title":"Quality and readability of online information on hand osteoarthritis","volume":"29","author":"Hong","year":"2023","journal-title":"Heal. Inform. J."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1437","DOI":"10.1001\/jamaoncol.2023.2947","article-title":"Assessment of Artificial Intelligence Chatbot Responses to Top Searched Queries About Cancer","volume":"9","author":"Pan","year":"2023","journal-title":"JAMA Oncol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"343","DOI":"10.1038\/s41746-025-01752-6","article-title":"Evaluating evidence-based health information from generative AI using a cross-sectional study with laypeople seeking screening information","volume":"8","author":"Rebitschek","year":"2025","journal-title":"npj Digit. Med."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"eaec8352","DOI":"10.1126\/science.aec8352","article-title":"Sycophantic AI decreases prosocial intentions and promotes dependence","volume":"391","author":"Cheng","year":"2026","journal-title":"Science"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1159","DOI":"10.1038\/s41586-026-10410-0","article-title":"Training language models to be warm can reduce accuracy and increase sycophancy","volume":"652","author":"Ibrahim","year":"2026","journal-title":"Nature"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Reis, M., Reis, F., Kim, Y.J., Demir, A., Lim, J., Gr\u00f6schel, M.I., Boie, S.D., and Kunde, W. (2026). Reduced symptom reporting quality during human\u2013chatbot versus human\u2013physician interactions. Nat. Health.","DOI":"10.1038\/s44360-026-00116-y"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"230","DOI":"10.1038\/s41586-020-2281-1","article-title":"The online competition between pro- and anti-vaccination views","volume":"582","author":"Johnson","year":"2020","journal-title":"Nature"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"e42758","DOI":"10.2196\/42758","article-title":"Conversational AI and Vaccine Communication: Systematic Review of the Evidence","volume":"25","author":"Passanante","year":"2023","journal-title":"J. Med. Internet Res."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"e2535813","DOI":"10.1001\/jamanetworkopen.2025.35813","article-title":"A Hybrid Chatbot to Promote Pneumococcal Vaccination Among Older Adults","volume":"8","author":"Wang","year":"2025","journal-title":"JAMA Netw. Open"},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"eadq1814","DOI":"10.1126\/science.adq1814","article-title":"Durably reducing conspiracy beliefs through dialogues with AI","volume":"385","author":"Costello","year":"2024","journal-title":"Science"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1780","DOI":"10.1038\/s42256-025-01113-8","article-title":"Language models cannot reliably distinguish belief from knowledge and fact","volume":"7","author":"Suzgun","year":"2025","journal-title":"Nat. Mach. Intell."}],"container-title":["Vaccines"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2076-393X\/14\/7\/594\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T09:06:46Z","timestamp":1783933606000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2076-393X\/14\/7\/594"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,3]]},"references-count":25,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2026,7]]}},"alternative-id":["vaccines14070594"],"URL":"https:\/\/doi.org\/10.3390\/vaccines14070594","relation":{},"ISSN":["2076-393X"],"issn-type":[{"value":"2076-393X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,3]]}}}