Benchmarking language models for postgraduate medical education on the Italian national specialty examination

Abstract excerpt

<title>Abstract</title> <p>Large language models (LLMs) are increasingly considered as educational tools for medical trainees, yet systematic evidence on their accuracy, robustness, and deployment feasibility remains limited. We evaluated 18 LLMs, specifically six proprietary, six open-source (1.7B–8B parameters), and six quantized variants of medically fine-tuned models, on the Italian national medical specialty...

Topics

Open a Topic to create a Post that cites this publication.

• Computational Biology
• BRCA1 gene
• GPT gene
• PTEN gene
• TP53 gene
• Genomics and Rare Diseases
• Phenotype
• Rare Diseases

Identifiers and source

Literature Corpus work

1ef7f4f1-d2ec-5f65-8192-3ac9f06f4755

DOI

10.21203/rs.3.rs-9722612/v1