ArticleScientific reports2025
The pitfalls of multiple-choice questions in generative AI and medical education.
Article in Scientific reports, 2025. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 14 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
14 citing papers in PubMed.
- Evaluating the Performance and Fragility of Large Language Models on the Self-Assessment for Neurological Surgeons.Neurosurgery · 2026Article
- Do Accuracy Gains Reflect Genuine Visual Understanding? A Multi-Model Evaluation of Vision-Language Models in Thoracic Imaging.Journal of imaging informatics in medicine · 2026Article
- Human-Edited Generative AI-Assisted Multiple-Choice Questions in Postgraduate Family Medicine: Blinded Cross-Sectional Comparative Psychometric Study.JMIR medical education · 2026Article
- Is artificial intelligence getting better at anatomy? A two-year review of ChatGPT's free public versions.Anatomical sciences education · 2026Article
- Automated Generation and Human Evaluation of Neurosurgical Board Examination Self-Assessment Questions.Neurosurgery practice · 2026Article
- Article
- AI in respiratory care: findings from the GOLD report.Journal of translational medicine · 2026Article
- ChatGPT as a tool for reviewing multiple-choice questions in the health sector.Scientific reports · 2026Article
- Cognitive reshaping and resurgence of humanness: restructuring the medical education continuum in the era of generative AI.Frontiers in medicine · 2026Review
- A comparative study of the performance of different large language models in the Chinese National Pharmacist Licensing Examination.Frontiers in medicine · 2026Article
- Benchmarking five large language models in medical genetics: a bilingual comparative evaluation using published and novel expert-authored questions.Frontiers in medicine · 2026Article
- Assessment of vaccine information accuracy across large language models.Frontiers in public health · 2026Article
- Generative artificial intelligence in medical education: from knowledge assessment to clinical reasoning and professional competence.Frontiers in medicine · 2026Review
- MedMobile: a mobile-sized language model with clinical capabilities.BMJ digital health & AI · 2025Article
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
12 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
The performance of Large Language Models (LLMs) on multiple-choice question (MCQ) benchmarks is frequently cited as proof of their medical capabilities. We hypothesized that LLM performance on medical MCQs may in part be illusory and driven by factors beyond medical content knowledge and reasoning capabilities. To assess this, we created a novel benchmark of free-response questions with paired MCQs (FreeMedQA). Using this benchmark, we evaluated three state-of-the-art LLMs (GPT-4o, GPT-3.5, and LLama-3-70B-instruct) and found an average absolute deterioration of 39.43% in performance on free-response questions relative to multiple-choice (p = 1.3 * 10
Indexed as
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.