Use of Large Language Models for Automated Short-Answer Question Grading in Second-Cycle Medical Education: Performance and Consistency Evaluation Study
JMIR Medical Education · 02.11.2026 · 12 · e89445
DOI: 10.2196/89445 ↗Kurz gefasst
Fachartikel in der Zeitschrift JMIR Medical Education, online erschienen am 02.11.2026. Verfasst von Sabrina Sidali und 4 weiteren Autor:innen. Beteiligte Einrichtung: Cordeliers Research Center, Sorbonne University, Inserm, University of Paris, Functional Genomics of Solid Tumors Team, French National Cancer League…. Hauptthemen laut MEDLINE: Large Language Models, Educational Measurement, Education, Medical. Die Arbeit nennt 21 Literaturangaben.
Abstract (Originalsprache)
Background
Short-answer questions (SAQs) effectively assess higher-order reasoning skills in medical education but face challenges in scalability due to time-intensive manual grading and concerns about interrater reliability. Recent advances in large language models (LLMs) may offer a solution through automated assessment.
Objective
This study evaluated the performance and consistency of LLMs—ChatGPT, Claude Sonnet 4, and Mistral Pro—compared with those of human graders for SAQ grading in hepatology and gastroenterology.
Methods
We retrospectively analyzed SAQs from hepatology and gastroenterology examinations at Sorbonne University, Paris, France (2023-2025). Three human evaluators (2 hepatogastroenterologists and 1 radiologist) independently graded all responses twice, with the majority consensus score serving as the reference standard. Six LLMs were evaluated: ChatGPT (GPT-4o, GPT-4.5, GPT-4o3, and GPT-5), Claude Sonnet 4, and Mistral Pro. Each LLM graded all responses twice using standardized prompts, including questions, model answers, grading guidelines, and scoring rubrics. Agreement was assessed using quadratic weighted kappa (QWK), Cohen κ, the intraclass correlation coefficient (ICC), and the mean absolute error (MAE) for interhuman, intrahuman, LLM-versus-human, and intramodel comparisons.
Results
A total of 902 student responses from 12 SAQs were included and analyzed. Interhuman grader agreement was almost perfect (QWK 0.90-0.92; ICC 0.90-0.92; MAE 0.05-0.07). Claude Sonnet 4 and GPT-4o3 demonstrated near-human–level performance when compared with the majority vote of human evaluators (Claude Sonnet 4: QWK 0.88-0.90; ICC 0.88-0.90; MAE 0.06-0.07 and GPT-4o3: QWK 0.82-0.89; ICC 0.82-0.89; MAE 0.07-0.09). GPT-5 showed substantial agreement (QWK 0.77-0.79). Mistral Pro and older ChatGPT versions performed poorly (QWK
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Cordeliers Research Center, Sorbonne University, Inserm, University of Paris, Functional Genomics of Solid Tumors Team, French National Cancer League-Accredited Team, Labex OncoImmunology, F-75006 Paris, Île-de-France,…
- University of Paris, Greater Paris University Hospitals (AP-HP), DMU DIGEST, Beaujon Hospital, Reference Center for Vascular Liver Diseases, FILFOIE, ERN RARE-LIVER, Inflammation Research Center, Inserm UMR 1149, Paris,…
- Sorbonne University, Inserm, Saint-Antoine Research Center (CRSA), Paris, Île-de-France, France.
- Saint-Antoine Hospital, Greater Paris University Hospitals (AP-HP), Paris, Île-de-France, France.
- Department of Radiology, Saint-Antoine Hospital, Greater Paris University Hospitals (AP-HP), Paris, Île-de-France, France.
- LIB, UMR 7371, Sorbonne University, CNRS, Inserm U1146, Paris, Île-de-France, France.
ORCID-Profile: Sabrina Sidali, Pierre-Antoine Soret, Mathilde Wagner, Thibault Voron, Quentin Vanderbecq
Zitieren
APA
Sidali, S., Soret, P. A., Wagner, M., Voron, T., & Vanderbecq, Q. (2026). Use of Large Language Models for Automated Short-Answer Question Grading in Second-Cycle Medical Education: Performance and Consistency Evaluation Study. JMIR Medical Education, 12, e89445. https://doi.org/10.2196/89445
Vancouver
Sidali S, Soret PA, Wagner M, Voron T, Vanderbecq Q. Use of Large Language Models for Automated Short-Answer Question Grading in Second-Cycle Medical Education: Performance and Consistency Evaluation Study. JMIR Medical Education. 2026;12:e89445. doi:10.2196/89445
BibTeX
@article{Sidali2026,
author = {Sidali, Sabrina and Soret, Pierre-Antoine and Wagner, Mathilde and Voron, Thibault and Vanderbecq, Quentin},
title = {Use of Large Language Models for Automated Short-Answer Question Grading in Second-Cycle Medical Education: Performance and Consistency Evaluation Study},
journal = {JMIR Medical Education},
year = {2026},
volume = {12},
pages = {e89445},
doi = {10.2196/89445}
}
EUVIMED