{"ID":2884386,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.06971","arxiv_id":"2508.06971","title":"Two-Stage Quranic QA via Ensemble Retrieval and Instruction-Tuned Answer Extraction","abstract":"Quranic Question Answering presents unique challenges due to the linguistic complexity of Classical Arabic and the semantic richness of religious texts. In this paper, we propose a novel two-stage framework that addresses both passage retrieval and answer extraction. For passage retrieval, we ensemble fine-tuned Arabic language models to achieve superior ranking performance. For answer extraction, we employ instruction-tuned large language models with few-shot prompting to overcome the limitations of fine-tuning on small datasets. Our approach achieves state-of-the-art results on the Quran QA 2023 Shared Task, with a MAP@10 of 0.3128 and MRR@10 of 0.5763 for retrieval, and a pAP@10 of 0.669 for extraction, substantially outperforming previous methods. These results demonstrate that combining model ensembling and instruction-tuned language models effectively addresses the challenges of low-resource question answering in specialized domains.","short_abstract":"Quranic Question Answering presents unique challenges due to the linguistic complexity of Classical Arabic and the semantic richness of religious texts. In this paper, we propose a novel two-stage framework that addresses both passage retrieval and answer extraction. For passage retrieval, we ensemble fine-tuned Arabic...","url_abs":"https://arxiv.org/abs/2508.06971","url_pdf":"https://arxiv.org/pdf/2508.06971v2","authors":"[\"Mohamed Basem\",\"Islam Oshallah\",\"Ali Hamdi\",\"Khaled Shaban\",\"Hozaifa Kassab\"]","published":"2025-08-09T12:37:19Z","proceeding":"cs.CL","tasks":"[\"cs.CL\",\"cs.IR\"]","methods":"[\"Language Model\"]","has_code":false}