| Title: | RAGCare-QA : a benchmark dataset for evaluating retrieval-augmented generation pipelines in theoretical medical knowledge |
|---|
| Authors: | ID Dobreva, Jovana (Author)
ID Karasmanakis, Ivana, Institut "Jožef Stefan" (Author)
ID Ivanisevic, Filip, Institut "Jožef Stefan" (Author)
ID Horvat, Tadej, Institut "Jožef Stefan" (Author)
ID Gams, Matjaž, Institut "Jožef Stefan" (Author)
ID Simjanoska Misheva, Monika (Author) |
|---|
| Files: |  URL - Source URL, visit https://www.sciencedirect.com/science/article/pii/S2352340925008674
 PDF - Presentation file, download (919,71 KB)
MD5: 095F423B47FF0E0B8227C1229E909D6F
Description: The dataset is available on Hugging Face Hub: https://huggingface.co/datasets/ChatMED-Project/RAGCare-QA.
|
|---|
| Language: | English |
|---|
| Typology: | 1.03 - Other scientific articles |
|---|
| Organization: |  IJS - Jožef Stefan Institute
|
|---|
| Abstract: | The paper introduces RAGCare-QA, an extensive dataset of 420 theoretical medical knowledge questions for assessing Retrieval-Augmented Generation (RAG) pipelines in medical education and evaluation settings. The dataset includes one-choice-only questions from six medical specialties (Cardiology, Endocrinology, Gastroenterology, Family Medicine, Oncology, and Neurology) with three levels of complexity (Basic, Intermediate, and Advanced). Each question is accompanied by the best fit of RAG implementation complexity level, such as Basic RAG (315 questions, 75.0 %), Multi-vector RAG (82 questions, 19.5 %), and Graph-enhanced RAG (23 questions, 5.5 %). The questions emphasize theoretical medical knowledge on fundamental concepts, pathophysiology, diagnostic criteria, and treatment principles important in medical education. The dataset is a useful tool for the assessment of RAG- based medical education systems, allowing researchers to fine-tune retrieval methods for various categories of theoretical medical knowledge questions. |
|---|
| Keywords: | medical education, retrieval-augmented generation, theoretical knowledge, multiple-choice questions |
|---|
| Publication status: | Published |
|---|
| Publication version: | Version of Record |
|---|
| Submitted for review: | 29.06.2025 |
|---|
| Article acceptance date: | 01.10.2025 |
|---|
| Publication date: | 09.10.2025 |
|---|
| Publisher: | Elsevier |
|---|
| Year of publishing: | 2025 |
|---|
| Number of pages: | str. 1-11 |
|---|
| Numbering: | Vol. 63, [article no.] 112146 |
|---|
| Source: | Nizozemska |
|---|
| PID: | 20.500.12556/DiRROS-25043  |
|---|
| UDC: | 004.8 |
|---|
| ISSN on article: | 2352-3409 |
|---|
| DOI: | 10.1016/j.dib.2025.112146 |
|---|
| COBISS.SI-ID: | 263916803 |
|---|
| Copyright: | © 2025 The Author(s). |
|---|
| Note: | Nasl. z nasl. zaslona;
Soavtorji iz Slovenije: Ivana Karasmanakis, Filip Ivanisevic, Tadej Horvat, Matjaž Gams;
Opis vira z dne 8. 1. 2026;
|
|---|
| Publication date in DiRROS: | 08.01.2026 |
|---|
| Views: | 237 |
|---|
| Downloads: | 62 |
|---|
| Metadata: |    |
|---|
|
:
|
Copy citation |
|---|
| | | | Share: |  |
|---|
Hover the mouse pointer over a document title to show the abstract or click
on the title to get all document metadata. |
