Metraipolis › archive › dc_7229583a1201
What Makes a Good Fiqh Retriever? Answer Retrieval for Arabic Islamic Jurisprudence — arXiv:2608.20246
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.20246
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T12:03:30.590Z
- SHA-256 of the archived text
dbb013f252caff7e3fb64e3b06b0f6dec19531722dbdae0b587a77f80163577f- Stable URL of this page
https://metraipolis.com/documento/dc_7229583a1201
How to cite
What Makes a Good Fiqh Retriever? Answer Retrieval for Arabic Islamic Jurisprudence — arXiv:2608.20246 — arXiv (en), https://arxiv.org/abs/2608.20246 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7229583a1201 (Metraipolis archive dc_7229583a1201, sha256 dbb013f252caff7e3fb64e3b06b0f6dec19531722dbdae0b587a77f80163577f)
BibTeX
@misc{dc7229583a1201,
title = {What Makes a Good Fiqh Retriever? Answer Retrieval for Arabic Islamic Jurisprudence — arXiv:2608.20246},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.20246},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7229583a1201; sha256 dbb013f252caff7e3fb64e3b06b0f6dec19531722dbdae0b587a77f80163577f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.20246. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Retrieval-Augmented Generation is used for Islamic question answering, but most systems are evaluated end-to-end, making retrieval failures difficult to isolate from generation failures. We study answer-bearing retrieval for Arabic fiqh, where a passage is relevant only if it states the ruling required by the question. We build a retrieval test collection for Arabic fiqh and use it to evaluate dense, lexical, hybrid, fine-tuned, and madhhab-aware retrieval strategies. The best retriever achieves 0.524 MRR@5, while fine-tuning improves performance to 0.553. Hybrid retrieval provides limited gains for strong models, whereas madhhab-aware filtering more than doubles MRR@5 on school-specific questions. We further present an error analysis showing that the main challenge is distinguishing answer-bearing passages from topically similar passages that do not contain the requested ruling. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-21 in cs.IR). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2608.20246 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T12:01:23.933Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-08-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).