MAWARITH: A Dataset and Benchmark for Legal Inheritance Reasoning with LLMs

Abstract

Islamic inheritance law is challenging for large language models because solving inheritance cases requires complex, structured, multi-step reasoning and the correct application of juristic rules to compute heirs' shares. We introduce \textit{MAWARITH}, a large-scale annotated dataset of 12,500 Arabic inheritance cases for training and evaluating models on the full reasoning chain: (i) identifying eligible heirs, (ii) applying blocking (\textit{\d{h}ajb}) and allocation rules, and (iii) computing exact inheritance shares. To the best of our knowledge, \textit{MAWARITH} is the first Arabic corpus and benchmark designed for end-to-end Islamic inheritance reasoning. Unlike prior datasets that restrict inheritance case solving to multiple-choice questions, \textit{MAWARITH} supports the full reasoning chain and provides step-by-step solutions with justifications grounded in classical juristic sources and established inheritance rules, as well as exact share calculations. This enables models to learn how to generate detailed, step-by-step responses to user queries that reflect real-world Islamic inheritance cases. To evaluate models beyond final-answer accuracy, we propose \textit{MIR-E} (Mawarith Inheritance Reasoning Evaluation), a weighted multi-stage metric that scores key reasoning stages and captures error propagation across the pipeline. We evaluate six large language models in a zero-shot setting. A commercial model achieves about 90\%, whereas all evaluated open-source models remain below 50\%. Our error analysis identifies recurring failure patterns, including scenario misinterpretation, errors in heir identification, errors in share allocation, and missing or incorrect application of key inheritance rules such as \textit{\textquotesingle awl} and \textit{radd}. The \textit{MAWARITH} dataset is publicly available at https://gitlab.com/nlpresearcher/mawarith.