mlsanityData to 14 Oct 2026

What Makes a Good Fiqh Retriever? Answer Retrieval for Arabic Islamic Jurisprudence

arXiv 2608.20246 ↗First posted 20 Aug 2026cs.IRcited by 0

On the map: Retrieval-augmented generation → RAG robustness and adaptive retrieval

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation. Builds on 13 of its 33 references that are in the map. First posted on arXiv 20 Aug 2026.

Builds on

13 of 33 references.

Closest ancestors · 1

Same direction, newest first

  1. 2026Grounding Arabic LLMs in the Doha Historical Dictionary: Retrieval-Augmented Understanding of Quran and Hadith25 Mar

Other references · 12

  1. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  2. 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,073
  3. 2024Arctic-Embed 2.0: Multilingual Retrieval Without Compromisecited by 58
  4. 2025Training Sparse Mixture Of Experts Text Embedding Modelscited by 32
  5. 2025Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questionscited by 10
  6. 2026From RAG to Agentic RAG for Faithful Islamic Question Answeringcited by 9
  7. 2024Improving LLM Reliability with RAG in Religious Question-Answering: MufassirQAScited by 6
  8. 2024Optimized Quran Passage Retrieval Using an Expanded QA Dataset and Fine-Tuned Language Modelscited by 5
  9. 2025GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Matryoshka Representation Learning and Hybrid Loss Trainingcited by 5
  10. 2023Leveraging Domain Adaptation and Data Augmentation to Improve Qur'anic IR in English and Arabiccited by 4
  11. 2025Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrievalcited by 4
  12. 2026QIAS 2026: Overview of the Shared Task on Islamic Inheritance Reasoningcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025FARSIQA: Faithful and Advanced RAG System for Islamic Question Answering
  2. 2025Transformer Tafsir at QIAS 2025 Shared Task: Hybrid Retrieval-Augmented Generation for Islamic Knowledge Question Answering
  3. 2025Investigating Retrieval-Augmented Generation in Quranic Studies: A Study of 13 Open-Source Large Language Models
  4. 2026Islamic Large Language Models: From Knowledge Acquisition to Trustworthy and Hallucination-Resistant AI
  5. 2026Fanar-Sadiq: A Multi-Agent Architecture for Grounded Islamic QA
  6. 2026ARMOR: Adaptive Retriever Optimization for Low-Resource Telecom Question Answering
  7. 2025Investigating the Robustness of Retrieval-Augmented Generation at the Query Level
  8. 2025Optimizing RAG Pipelines for Arabic: A Systematic Analysis of Core Components