MedLingua at MedArabiQ2025: Zero- and Few-Shot Prompting of Large Language Models for Arabic Medical QA
Bibliographic record
Abstract
This paper details the system developed by team MedLingua for the MedArabiQ2025 Shared Task, specifically participating in Track 2, Sub-Task 1: Multiple Choice Question Answering.Our approach centered on evaluating the zero-shot and few-shot capabilities of various Large Language Models (LLMs) on Arabic medical questions, as fine-tuning was not permitted.We systematically tested a range of models, from general-purpose state-of-the-art LLMs like Google's Gemini 2.5 Pro to specialized medical models such as BiMediX2 and MedGemma.Our findings reveal that advanced, general-domain models significantly outperform specialized medical LLMs that are not optimized for Arabic.Our best performing system, using Gemini 2.5 Pro, achieved an accuracy of 78% in the development set and 74% on the blind test set, securing the 3rd place on the official competition leaderboard.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.004 | 0.013 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.004 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.002 | 0.003 |
| Insufficient payload (model declined to judge) | 0.028 | 0.014 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".