EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Performance of Enhanced Large Language Models on Prosthodontic Multiple-Choice Questions

Shenghan Gao, Zi-Ang Wang, Zihan Gao, Jiaxuan Liu, Huishuai Zhang, Shaoxia Pan, Yongsheng Zhou

International Dental Journal · 2026

DOI: 10.1016/j.identj.2026.109441 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Dental Journal, 2026. Verfasst von Shenghan Gao und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Prosthodontics, Peking University School and Hospital of Stomatology & National Center for Stomatology & National Clinical Research Cen…. Hauptthemen laut MEDLINE: Large Language Models, Prosthodontics, Educational Measurement, Education, Dental. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Peking University, Peking University Health Science Center.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

OBJECTIVES: To evaluate the performance of retrieval-augmented generation (RAG), in-context learning (ICL) and majority voting-enhanced large language models (LLMs) on prosthodontic questions. METHODS: Two LLMs, OpenAI o1 and DeepSeek-R1, were used as base models in this study. The base models were enhanced using RAG, ICL and majority voting. The resulting enhanced LLMs-enhanced DeepSeek-R1 and enhanced OpenAI o1-were evaluated alongside their original counterparts. Standardised Chinese-language and English-language prosthodontics questions were used to evaluate the performance of the base and enhanced LLMs. The correctness of each answer and the error types were recorded. χ2 tests were used to compare differences among the 4 LLMs (α = 0.05). RESULTS: Enhanced versions of both DeepSeek-R1 and OpenAI o1 achieved significant accuracy improvement compared with their base versions in Chinese-language multiple-choice questions (C-MCQs) (P < .001). In English-language multiple-choice questions (E-MCQs), both enhanced versions also exhibited higher accuracy, but the difference was not statistically significant (P = .145). In error analysis, enhanced LLMs significantly reduced knowledge-based errors in C-MCQs (P < .008) but showed only a non-significant reduction in E-MCQs (P = .604). The results reveal that the significant improvement gains from model enhancement were confined to C-MCQs and were not observed in E-MCQs. CONCLUSIONS: The LLMs enhanced using inference-time strategies including RAG, ICL and majority voting show significantly improved accuracy in answering C-MCQs. Although this approach effectively mitigates errors, our analysis reveals a lack of consistent statistically significant improvements in E-MCQs. CLINICAL SIGNIFICANCE: This study illustrates the performance of enhanced LLMs in analysing prosthodontics questions with good accuracy and potential in dentistry education. This implies that enhanced LLMs may be more suitable than non-enhanced ones for processing dental-related tasks.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Large Language ModelsProsthodonticsEducational MeasurementEducation, DentalHumans

Stichwörter der Autor:innen

Artificial intelligenceEducationLarge language modelsProsthodonticsRetrieval‐augmented generation

Autor:innen und Institutionen

  • Department of Prosthodontics, Peking University School and Hospital of Stomatology & National Center for Stomatology & National Clinical Research Center for Oral Diseases & National Engineering Research Center of Oral B…
  • School of Electronics Engineering and Computer Science, Peking University, Beijing, PR China.
  • School of Basic Medical Sciences, Peking University, Beijing, PR China.
  • Wangxuan Institute of Computer Technology, Peking University, Beijing, PR China. Electronic address: zhanghuishuai@pku.edu.cn.

Förderung

  • Peking University
  • Peking University Health Science Center

Zitieren

APA

Gao, S., Wang, Z. A., Gao, Z., Liu, J., Zhang, H., Pan, S., & Zhou, Y. (2026). Performance of Enhanced Large Language Models on Prosthodontic Multiple-Choice Questions. International Dental Journal. https://doi.org/10.1016/j.identj.2026.109441

Vancouver

Gao S, Wang ZA, Gao Z, Liu J, Zhang H, Pan S, et al. Performance of Enhanced Large Language Models on Prosthodontic Multiple-Choice Questions. International Dental Journal. 2026. doi:10.1016/j.identj.2026.109441

BibTeX
@article{Gao2026,
  author = {Gao, Shenghan and Wang, Zi-Ang and Gao, Zihan and Liu, Jiaxuan and Zhang, Huishuai and Pan, Shaoxia and Zhou, Yongsheng},
  title = {Performance of Enhanced Large Language Models on Prosthodontic Multiple-Choice Questions},
  journal = {International Dental Journal},
  year = {2026},
  doi = {10.1016/j.identj.2026.109441}
}
Kostenlos starten →