Published July 12, 2025
| Version v2
Dataset
Open
HIVMedQA
Contributors
Project leader (3):
- 1. Department of Biosystems Science and Engineering, ETH Zurich, Basel, Switzerland
- 2. School of Life Sciences, École Polytechnique Fédérale de Lausanne, Lausanne, Switzerland
- 3. Swiss Institute of Bioinformatics, Lausanne, Switzerland
- 4. Biomedical Data Science Center, Lausanne University Hospital and University of Lausanne, Lausanne, Switzerland
- 5. Institute of Medical Virology, University of Zurich, Zurich, Switzerland
- 6. Department of Infectious Diseases and Hospital Epidemiology, University Hospital Zurich, Zurich, Switzerland
- 7. ETH AI Center, ETH Zurich, Zurich, Switzerland
- 8. Department of Quantitative Biomedicine, University of Zurich, Zurich, Switzerland
- 9. Department of Infectious Diseases and Hospital Epidemiology, University Hospital Zurich and University of Zurich, Zürich, Switzerland
Description
This dataset supports the findings presented in the article HIVMedQA: Benchmarking large language models for HIV medical decision support. It comprises two components:
-
questions.csv : Contains all the questions, the corresponding gold-standard answers, and their sources.
-
all_questions_answers_scores.csv : Includes the responses generated by LLMs, along with evaluation scores.
-
all_questions_answers_scores_unsupervised.csv: Includes the evaluation scores under the unsupervised setting.
- all_questions_answers_scores_withRAG_withInfoInGuidelines.csv: Includes the responses generated by LLMs with using RAG and their associated evaluation scores.
If you use this dataset in your work, please cite: Cardenal-Antolin, Gonzalo, et al. "HIVMedQA: Benchmarking large language models for HIV medical decision support." arXiv preprint arXiv:2507.18143 (2025).