Arabic judicial narratives matched to Saudi family and evidence law articles
Statutory Article Retrieval from Arabic Judicial Narratives: Family Law and Law of Evidence in Saudi Arabia
Computation and LanguageArtificial Intelligence
Summary
Finding the right laws for complicated Arabic court stories is hard because the stories are long and the laws are short and abstract. The authors tested different ways to link these stories to the correct Saudi laws on family and evidence using a new method called Decompose-and-Refine (DaR). This method breaks down court stories into issues and searches laws in several ways, which gave much better results for both types of law. Without this, the best tools worked well only for family law but not evidence law. DaR helped one approach work well for both.
What this means in practice
- •For legal tech developers: Automate retrieval of relevant Saudi family and evidence law articles from Arabic court narratives to support legal reasoning systems.
- •For government legal departments: Improve access to authoritative statutory articles for judges and lawyers by linking case narratives with legal rules more accurately.
Authors
Zarah Shibli, Areej Alhothali, Lulwah Alharigy
Abstract
Reliable legal information retrieval must ground legal reasoning in authoritative statutory sources. In Arabic judicial settings, long factual narratives must be mapped to concise articles that express abstract legal rules, creating a narrative-to-legal-rule abstraction gap. Using a benchmark of 200 synthetic Saudi Arabic judicial cases and 381 articles from the Family Law and the Law of Evidence, we compare word-level and char-4 BM25, zero-shot dense encoders, per-law retrieval, dense-sparse reciprocal rank fusion (RRF), and a proposed Decompose-and-Refine (DaR) pipeline. In DaR, a large language model splits each narrative into disputed legal issues and generates, for each issue, three retrieval channels: a statute-style paraphrase, legal keywords, and a candidate taxonomy chapter. On the whole corpus, the instructed Qwen3-Embedding-8B dense encoder reaches an MRR@10 of 0.849, the best result of any non-decomposed system. Under per-law scoring, this advantage reflects Family Law only: restricted to Evidence articles, the same encoder drops to an MRR@10 of 0.087, and fusion with BM25 raises it only to 0.207. DaR changes this picture, raising Evidence MRR@10 to 0.696 and Family MRR@10 to 0.864. Without decomposition, the two laws favor different strategies; under DaR, the same retriever achieves the best MRR@10 on both.