AI Paper Atlas

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

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Knowledge-augmented question answering · 8 citations (OpenAlex)

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 changedWhereMeasuredEffect
fine-tune with QLoRA on the MedAraBench training splitLlama-3.1-8B-Instruct · MedAraBench testaccuracy: 0.170 -> 0.320Improved
add 3 in-context examples (few-shot)Llama-3.1-8B-Instruct · MedAraBench testaccuracy: 0.170 -> 0.191Improved
use reasoning models (GPT-5, GPT-o3) instead of non-reasoning proprietary modelsproprietary LLMs · MedAraBench testaccuracy: 0.673 (GPT-4.1) -> 0.765 (GPT-o3)Improved
use Arabic-centric or medical-specific models instead of larger general-purpose modelsopen-source LLMs · MedAraBench testaccuracy: 0.547 (Llama-3.3-70B) vs 0.447 (ALLaM-7B), 0.390 (MedGemma-4B)Hurt
use newer contemporary models instead of legacy modelsMedArabiQ MCQ · MedArabiQ MCQaccuracy: 0.535 (gpt-4) -> 0.8586 (gpt-5)Improved
switch benchmark from MedArabiQ to MedAraBenchGPT-5 · MedArabiQ vs MedAraBenchaccuracy: 0.8586 -> 0.7642Hurt

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy