EUVIMEDEUVIMED entdecken
Crossref

Arabian Nights or English Days? Accuracy of Large Language Models in Answering Bilingual Dental Multiple‐Choice Questions

Hala Alanazi, Lujain Altalhi, Nadeen Alanazi, Reem Al Ghamdi, Ali Anwar Aboalela, Sohaib Shujaat iD

European Journal of Dental Education · 2026-05 · 30 (2) · 707-715

DOI: 10.1111/eje.70018 ↗

Kurz gefasst

Fachartikel in der Zeitschrift European Journal of Dental Education, online erschienen am 03.11.2025. Verfasst von Hala Alanazi und 5 weiteren Autor:innen. Beteiligte Einrichtung: King Abdullah International Medical Research Center, College of Dentistry, King Saud Bin Abdulaziz University for Health Sciences, Ministry of Nation…. Hauptthemen laut MEDLINE: Multilingualism, Education, Dental, Language, Educational Measurement. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 39 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

While large language models (LLMs) perform well in medical education, their ability to accurately interpret and answer English and Arabic dental multiple‐choice questions (MCQs) remains underexplored.

Aims

This study evaluated the performance of advanced LLMs in answering dental MCQs in both languages, identifying language‐specific challenges and assessing their applicability in multilingual dental education. Materials and Methods A total of 300 MCQs from ten dental specialties were sourced from question banks. The MCQs were translated into Arabic and reviewed for linguistic and technical accuracy. Four LLMs, ChatGPT‐4o, ChatGPT‐4, Gemini, and Claude, were tested separately on Arabic and English datasets. Accuracy was the primary metric, along with specialty‐specific performance, question type differentiation, and cross‐language consistency.

Results

Claude achieved the highest accuracy in English (89%), while Gemini performed best in Arabic (80%). Most models showed better performance in English, with notable translation inconsistencies, particularly for ChatGPT models. Specialty‐wise, Claude and Gemini excelled in endodontics and operative dentistry. No significant differences were observed between knowledge‐based and clinical questions, but Arabic interpretation posed challenges. Statistical analysis confirmed significant differences between models and across languages.

Discussion

Gemini demonstrated robust performance in Arabic, while Claude excelled in English. ChatGPT models exhibited limitations, particularly in Arabic datasets. Performance varied across specialties, highlighting the need for improved multilingual adaptability and specialty‐specific training.

Conclusion

Expanding specialised and culturally relevant datasets is essential for optimising LLMs' educational utility. This study provides key insights into LLM performance in bilingual dental education, supporting future advancements in AI‐driven learning tools.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

MultilingualismEducation, DentalLanguageEducational MeasurementHumansSurveys and QuestionnairesLarge Language Models

Stichwörter der Autor:innen

Arabic languageartificial intelligencedental educationmultilingualismnatural language processing

Autor:innen und Institutionen

  • King Abdullah International Medical Research Center, College of Dentistry, King Saud Bin Abdulaziz University for Health Sciences, Ministry of National Guard Health Affairs, Riyadh, Kingdom of Saudi Arabia.
  • King Abdullah International Medical Research Center, Department of Restorative and Prosthetic Dental Sciences, College of Dentistry, King Saud Bin Abdulaziz University for Health Sciences, Ministry of National Guard Hea…
  • King Abdullah International Medical Research Center, Department of Maxillofacial Surgery and Diagnostic Sciences, College of Dentistry, King Saud bin Abdulaziz University for Health Sciences, Ministry of National Guard…
  • OMFS-IMPATH Research Group, Department of Imaging and Pathology, Faculty of Medicine, KU Leuven, & Department of Oral and Maxillofacial Surgery, University Hospitals Leuven, Leuven, Belgium.

ORCID-Profile: Sohaib Shujaat

Zitieren

APA

Alanazi, H., Altalhi, L., Alanazi, N., Al Ghamdi, R., Aboalela, A. A., & Shujaat, S. (2026). Arabian Nights or English Days? Accuracy of Large Language Models in Answering Bilingual Dental Multiple‐Choice Questions. European Journal of Dental Education, 30(2), 707-715. https://doi.org/10.1111/eje.70018

Vancouver

Alanazi H, Altalhi L, Alanazi N, Al Ghamdi R, Aboalela AA, Shujaat S. Arabian Nights or English Days? Accuracy of Large Language Models in Answering Bilingual Dental Multiple‐Choice Questions. European Journal of Dental Education. 2026;30(2):707-715. doi:10.1111/eje.70018

BibTeX
@article{Alanazi2026,
  author = {Alanazi, Hala and Altalhi, Lujain and Alanazi, Nadeen and Al Ghamdi, Reem and Aboalela, Ali Anwar and Shujaat, Sohaib},
  title = {Arabian Nights or English Days? Accuracy of Large Language Models in Answering Bilingual Dental Multiple‐Choice Questions},
  journal = {European Journal of Dental Education},
  year = {2026},
  volume = {30},
  number = {2},
  pages = {707--715},
  doi = {10.1111/eje.70018}
}
Kostenlos starten →