# !MSA at AraHealthQA 2025 Shared Task: Enhancing LLM Performance for Arabic Clinical Question Answering through Prompt Engineering and Ensemble Learning

Source: [!MSA at AraHealthQA 2025 Shared Task: Enhancing LLM Performance for Arabic Clinical Question Answering through Prompt Engineering and Ensemble Learning](<https://www.sota2.com/research/paper/68fa7b551e209131cea87dd2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T07:01:39.544Z

Authors: Mohamed Tarek, Seif Ahmed, Mohamed Basem

Published: 2025-09-14T17:39:58.000Z

## Abstract

We present our systems for Track 2 (General Arabic Health QA, MedArabiQ) of the AraHealthQA-2025 shared task, where our methodology secured 2nd place in both Sub-Task 1 (multiple-choice question answering) and Sub-Task 2 (open-ended question answering) in Arabic clinical contexts. For Sub-Task 1, we leverage the Gemini 2.5 Flash model with few-shot prompting, dataset preprocessing, and an ensemble of three prompt configurations to improve classification accuracy on standard, biased, and fill-in-the-blank questions. For Sub-Task 2, we employ a unified prompt with the same model, incorporating role-playing as an Arabic medical expert, few-shot examples, and post-processing to generate concise responses across fill-in-the-blank, patient-doctor Q&A, GEC, and paraphrased variants.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2509.11365>)

[PDF](<https://arxiv.org/pdf/2509.11365.pdf>)