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

• 类型：arxiv
• 标识：2608.20246
• 链接：http://arxiv.org/abs/2608.20246v1
• 主分类：rag
• 形态：method
• TLDR：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 gai
• 副分类：evaluation
• 待LLM分类：否
• 标题中文：怎样的 Fiqh 检索器才算好？面向阿拉伯伊斯兰法学的答案检索
• TLDR中文：RAG 被用于伊斯兰问答，但多数系统采用端到端评估，难以区分检索失败与生成失败。本文研究阿拉伯 fiqh 的"承载答案的检索"——仅当段落陈述问题所需裁决时才视为相关。我们构建了阿拉伯 fiqh 检索测试集，并评估 dense、lexical、hybrid、fine-tuned 及 madhhab-aware 检索策略。最佳检索器 MRR@5 达 0.524，fine-tuning 进一步提升至 0.553；hybrid retrieval 增益有限（原文截断）。
• 来源文件：
• /inbox/tom/_candidates/2026-08-22-agent-rag-longcontext-candidates.json
• /inbox/tom/_candidates/2026-08-23-agent-rag-longcontext-candidates.json