CUREv1: Clinical Understanding & Retrieval Evaluation Across 10 Disciplines

CUREv1 is a dataset for evaluating retrieval systems on query-passage pairs curated by medical professionals. It spans 10 clinical disciplines and includes 3 cross-lingual settings. The dataset was created by Clinia and last updated on December 11, 2024.

Use Cases

• Benchmarking medical information retrieval systems based on professionally curated query-passage pairs.
• Evaluating cross-lingual retrieval performance in clinical settings as described.
• Training or fine-tuning retrievers for specific medical disciplines like dermatology.

Strengths

• Query-passage pairs were curated by medical professionals.
• Covers 10 distinct clinical disciplines.
• Includes 3 cross-lingual evaluation settings.

Limitations

• Row count, file formats, and column-level documentation are unknown, limiting suitability assessment.
• License information is unavailable, which may restrict usage.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

Clinia

Collection Method

Curated by medical professionals.

Freshness

Last updated 2024-12-11 14:06:07.