Medical Exams Pes Pl 2007 2024

The medical-exams-PES-PL-2007-2024 dataset is described in a 2024 arXiv preprint by researchers including Łukasz Grzybowski. It is a Polish medical exam dataset intended for assessing cross-lingual medical knowledge transfer. The dataset page is hosted on Hugging Face by the author amu-cai and was last updated in August 2025.

Use Cases

• Assessing cross-lingual medical knowledge transfer based on the dataset's stated purpose.
• Training or evaluating medical question-answering models based on exam questions.
• Analyzing the difficulty and structure of Polish medical licensing exams over time based on the 2007-2024 time range.

Strengths

• Dataset is associated with a peer-reviewed arXiv preprint from 2024, providing academic context.
• The time range (2007-2024) suggests longitudinal coverage of exam content.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and file size are unknown, which may limit suitability assessment.
• Data may reflect geographic and linguistic bias inherent to its Polish-language source.

Provenance

Source

amu-cai on Hugging Face, associated with the research paper 'Polish medical exams: A new dataset for cross-lingual medical knowledge transfer assessment'.

Time Range

2007 to 2024

Freshness

Last updated 2025-08-11 09:57:19; freshness should be verified.

Geography

Poland