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

arXiv: https://arxiv.org/abs/2608.20246 · HTML: https://mlsanity.com/paper/2608.20246/

## 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.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Builds on (most cited first, 13 of 13)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillation](https://mlsanity.com/paper/2402.03216/) (2024)
- [Arctic-Embed 2.0: Multilingual Retrieval Without Compromise](https://mlsanity.com/paper/2412.04506/) (2024)
- [Training Sparse Mixture Of Experts Text Embedding Models](https://mlsanity.com/paper/2502.07972/) (2025)
- [Sacred or Synthetic? Evaluating LLM Reliability and Abstention for Religious Questions](https://mlsanity.com/paper/2508.08287/) (2025)
- [From RAG to Agentic RAG for Faithful Islamic Question Answering](https://mlsanity.com/paper/2601.07528/) (2026)
- [Improving LLM Reliability with RAG in Religious Question-Answering: MufassirQAS](https://mlsanity.com/paper/2401.15378/) (2024)
- [Optimized Quran Passage Retrieval Using an Expanded QA Dataset and Fine-Tuned Language Models](https://mlsanity.com/paper/2412.11431/) (2024)
- [GATE: General Arabic Text Embedding for Enhanced Semantic Textual Similarity with Matryoshka Representation Learning and Hybrid Loss Training](https://mlsanity.com/paper/2505.24581/) (2025)
- [Leveraging Domain Adaptation and Data Augmentation to Improve Qur'anic IR in English and Arabic](https://mlsanity.com/paper/2312.02803/) (2023)
- [Multi-stage Training of Bilingual Islamic LLM for Neural Passage Retrieval](https://mlsanity.com/paper/2501.10175/) (2025)
- [QIAS 2026: Overview of the Shared Task on Islamic Inheritance Reasoning](https://mlsanity.com/paper/2606.13756/) (2026)
- [Grounding Arabic LLMs in the Doha Historical Dictionary: Retrieval-Augmented Understanding of Quran and Hadith](https://mlsanity.com/paper/2603.23972/) (2026)

## 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.