!MSA at AraHealthQA 2025 Shared Task: Enhancing LLM Performance for Arabic Clinical Question Answering through Prompt Engineering and Ensemble Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912586128162816 |
|---|---|
| author | Tarek, Mohamed Ahmed, Seif Basem, Mohamed |
| author_facet | Tarek, Mohamed Ahmed, Seif Basem, Mohamed |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_11365 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | !MSA at AraHealthQA 2025 Shared Task: Enhancing LLM Performance for Arabic Clinical Question Answering through Prompt Engineering and Ensemble Learning Tarek, Mohamed Ahmed, Seif Basem, Mohamed Computation and Language 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. |
| title | !MSA at AraHealthQA 2025 Shared Task: Enhancing LLM Performance for Arabic Clinical Question Answering through Prompt Engineering and Ensemble Learning |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.11365 |