用检索增强生成技术解决伊斯兰继承法复杂计算问题
CVPD at QIAS 2026: RAG-Guided LLM Reasoning for Al-Mawarith Share Computation and Heir Allocation
- 基于规则生成合成数据，结合混合检索与校验机制
- 在QIAS 2026评测中达MIR-E 0.935，排名第一
- 适合法律AI、阿拉伯语高精度推理场景
伊斯兰继承（Ilm al-Mawarith）是一项多阶段法律推理任务，需识别合格继承人、处理阻断规则（hajb）、分配固定与剩余份额、调整如awl和radd，并生成一致的最终分配。该任务因不同法学派别和民法典差异而复杂，要求模型在明确法律配置下运行。我们提出一种检索增强生成（RAG）流程，结合规则驱动的合成数据生成、混合检索（稠密+BM25）与交叉编码器重排序，以及模式约束输出验证。采用符号继承计算器生成包含完整中间推理过程的大规模高质量合成语料库，确保法律与数值一致性。所提系统在官方QIAS 2026盲测排行榜上取得MIR-E 0.935得分，位居第一。结果表明，基于检索与模式感知的生成显著提升高精度阿拉伯语法律推理的可靠性。
原文摘要 · Abstract (English)
Islamic inheritance (Ilm al-Mawarith) is a multi-stage legal reasoning task requiring the identification of eligible heirs, resolution of blocking rules (hajb), assignment of fixed and residual shares, handling of adjustments such as awl and radd, and generation of a consistent final distribution. The task is further complicated by variations across legal schools and civil-law codifications, requiring models to operate under explicit legal configurations. We present a retrieval-augmented generation (RAG) pipeline for this setting, combining rule-grounded synthetic data generation, hybrid retrieval (dense and BM25) with cross-encoder reranking, and schema-constrained output validation. A symbolic inheritance calculator is used to generate a large high-quality synthetic corpus with full intermediate reasoning traces, ensuring legal and numerical consistency. The proposed system achieves a MIR-E score of 0.935 and ranks first on the official QIAS 2026 blind-test leaderboard. Results demonstrate that retrieval-grounded, schema-aware generation significantly improves reliability in high-precision Arabic legal reasoning tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。