EUVIMEDObjevte EUVIMED
Open access

Prompt Framing and Evidence Requirement for AI-Generated Educational Responses in Dental Education: Experimental Study

Man Hung iD, Corban Ward iD, Owen Cohen iD, Jacob Marx iD, Zachary Smit iD, Jacob Newman iD, Martin S Lipsky iD

JMIR Medical Education · 2026-08-06 · 12 · e90736-e90736

DOI: 10.2196/90736 ↗

At a glance

Journal article in JMIR Medical Education, published online on 2026-08-06. Written by Man Hung and 6 co-authors. Institution: College of Dental Medicine, Roseman University of Health Sciences, 10894 S. River Front Parkway, South Jordan, UT, 84095, United States, 1 8018781270. Major MEDLINE topics: Education, Dental, Artificial Intelligence. 29 references. The full text is freely available in PubMed Central.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Large language models are increasingly used in health professions education; however, the role of prompt design in shaping their outputs remains poorly understood in clinical training contexts. In dentistry, where information presentation, perceived credibility, and procedural reasoning are important, the effects of instructional framing and evidence requirements on AI-generated educational responses are particularly relevant.

Objective

This study examined whether instructional framing and evidence requirements were associated with rater-assessed perceived factuality, tone, stance orientation, citation behavior, safety notices, hedging, and response length in responses about cavity preparation generated using GPT-5 through its web-based interface.

Methods

In a 2×2 factorial experiment, we manipulated instructional framing (patient-centered vs skill-centered) and evidence requirement (evidence-required vs no evidence) across 10 base prompt topics and 4 experimental conditions, yielding 40 outputs. Five trained raters independently coded each response for perceived factuality, confidence tone, stance orientation, hedging, citation presence, and safety notices. Response length was calculated programmatically. Interrater reliability was assessed using intraclass correlation coefficients and Fleiss κ. Consensus measures were analyzed using factorial analyses of variance and chi-square tests.

Results

Evidence requirement was associated with greater citation presence (19/20, 95% vs 5/20, 25%; P

Subjects

MeSH terms (MEDLINE)

Education, DentalArtificial IntelligenceHumansLarge Language ModelsGenerative Artificial IntelligenceReproducibility of Results

Author keywords

ChatGPTartificial intelligencedental educationevidence-based practicelarge language modelsprompt engineering

Authors and institutions

  • College of Dental Medicine, Roseman University of Health Sciences, 10894 S. River Front Parkway, South Jordan, UT, 84095, United States, 1 8018781270.
  • Department of Family Medicine and Public Health, University of Utah, Salt Lake City, UT, United States.
  • Department of Education Psychology, University of Utah, Salt Lake City, UT, United States.
  • Institute on Aging, Portland State University, Portland, OR, United States.

ORCID profiles: Man Hung, Corban Ward, Owen Cohen, Jacob Marx, Zachary Smit, Jacob Newman, Martin S Lipsky

Cite

APA

Hung, M., Ward, C., Cohen, O., Marx, J., Smit, Z., Newman, J., & Lipsky, M. S. (2026). Prompt Framing and Evidence Requirement for AI-Generated Educational Responses in Dental Education: Experimental Study. JMIR Medical Education, 12, e90736-e90736. https://doi.org/10.2196/90736

Vancouver

Hung M, Ward C, Cohen O, Marx J, Smit Z, Newman J, et al. Prompt Framing and Evidence Requirement for AI-Generated Educational Responses in Dental Education: Experimental Study. JMIR Medical Education. 2026;12:e90736-e90736. doi:10.2196/90736

BibTeX
@article{Hung2026,
  author = {Hung, Man and Ward, Corban and Cohen, Owen and Marx, Jacob and Smit, Zachary and Newman, Jacob and Lipsky, Martin S},
  title = {Prompt Framing and Evidence Requirement for AI-Generated Educational Responses in Dental Education: Experimental Study},
  journal = {JMIR Medical Education},
  year = {2026},
  volume = {12},
  pages = {e90736--e90736},
  doi = {10.2196/90736}
}
Start for free →