Polish-English medical knowledge transfer: A new benchmark and results
This addresses the problem of language bias in medical AI for Polish healthcare, though it is incremental as it applies existing methods to new data.
This study tackled the lack of non-English benchmarks for LLMs in medical tasks by introducing a new dataset of over 24,000 Polish medical exam questions, revealing that models like GPT-4o achieve near-human performance but struggle with cross-lingual translation and domain-specific understanding.
Large Language Models (LLMs) have demonstrated significant potential in handling specialized tasks, including medical problem-solving. However, most studies predominantly focus on English-language contexts. This study introduces a novel benchmark dataset based on Polish medical licensing and specialization exams (LEK, LDEK, PES) taken by medical doctor candidates and practicing doctors pursuing specialization. The dataset was web-scraped from publicly available resources provided by the Medical Examination Center and the Chief Medical Chamber. It comprises over 24,000 exam questions, including a subset of parallel Polish-English corpora, where the English portion was professionally translated by the examination center for foreign candidates. By creating a structured benchmark from these existing exam questions, we systematically evaluate state-of-the-art LLMs, including general-purpose, domain-specific, and Polish-specific models, and compare their performance against human medical students. Our analysis reveals that while models like GPT-4o achieve near-human performance, significant challenges persist in cross-lingual translation and domain-specific understanding. These findings underscore disparities in model performance across languages and medical specialties, highlighting the limitations and ethical considerations of deploying LLMs in clinical practice.