什么样的伊斯兰教法检索器是优秀的？阿拉伯伊斯兰教法的答案检索
What Makes a Good Fiqh Retriever? Answer Retrieval for Arabic Islamic Jurisprudence
浏览论文内容
中文总结 AI 辅助
本研究针对阿拉伯伊斯兰教法构建检索测试集，评估多种检索策略，发现教法学派感知过滤可显著提升教派特定问题的检索性能，核心挑战是区分答案承载与主题相似的非答案段落。
中文摘要 AI 辅助
检索增强生成技术被用于伊斯兰问答任务，但大多数系统采用端到端评估，难以区分检索失败与生成失败。本研究针对阿拉伯伊斯兰教法（fiqh）开展答案承载段落的检索研究，定义仅当段落陈述问题所需的裁决（ruling）时才为相关。我们构建了阿拉伯伊斯兰教法的检索测试集，用于评估密集型、词汇型、混合型、微调型以及教法学派（madhhab）感知的检索策略。最优检索器的MRR@5达0.524，微调后性能提升至0.553；混合型检索对强模型增益有限，而教法学派感知过滤在教派特定问题上使MRR@5提升超一倍。进一步的错误分析显示，核心挑战是区分答案承载段落与主题相似但不含所需裁决的段落。
英文摘要
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.
