Research map / Large language models / Retrieval and knowledge
MedAraBench: Large-scale Arabic Medical Question Answering Dataset and Benchmark
Mouath Abu Daoud, Leen Kharouf, Omar El Hajj, Dana El Samad, Mariam Al-Omari, Jihad Mallat, Khaled Saleh, Nizar Habash, Farah E. Shamout
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| fine-tune with QLoRA on the MedAraBench training split | Llama-3.1-8B-Instruct · MedAraBench test | accuracy: 0.170 -> 0.320 | Improved |
| add 3 in-context examples (few-shot) | Llama-3.1-8B-Instruct · MedAraBench test | accuracy: 0.170 -> 0.191 | Improved |
| use reasoning models (GPT-5, GPT-o3) instead of non-reasoning proprietary models | proprietary LLMs · MedAraBench test | accuracy: 0.673 (GPT-4.1) -> 0.765 (GPT-o3) | Improved |
| use Arabic-centric or medical-specific models instead of larger general-purpose models | open-source LLMs · MedAraBench test | accuracy: 0.547 (Llama-3.3-70B) vs 0.447 (ALLaM-7B), 0.390 (MedGemma-4B) | Hurt |
| use newer contemporary models instead of legacy models | MedArabiQ MCQ · MedArabiQ MCQ | accuracy: 0.535 (gpt-4) -> 0.8586 (gpt-5) | Improved |
| switch benchmark from MedArabiQ to MedAraBench | GPT-5 · MedArabiQ vs MedAraBench | accuracy: 0.8586 -> 0.7642 | Hurt |
Closest papers by meaning
- MedBench: A Large-Scale Chinese Benchmark for Evaluating Medical Large Language Models (AAAI 2024 · similarity 0.88)
- Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks (NeurIPS 2026 · similarity 0.88)
- MedJourney: Benchmark and Evaluation of Large Language Models over Patient Clinical Journey (NeurIPS 2024 · similarity 0.87)
- Multi-OphthaLingua: A Multilingual Benchmark for Assessing and Debiasing LLM Ophthalmological QA in LMICs (AAAI 2025 · similarity 0.87)
- MedCalc-Bench: Evaluating Large Language Models for Medical Calculations (NeurIPS 2024 · similarity 0.86)
- Chiron-o1: Igniting Multimodal Large Language Models towards Generalizable Medical Reasoning via Mentor-Intern Collaborative Search (NeurIPS 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
