MoroccoRegQA

MoroccoRegQA is an Arabic regulatory retrieval benchmark comprising 90 expert-annotated query–evidence pairs grounded in five Moroccan legal codes and a parsed corpus of 2,464 hierarchically structured articles (moroccanregdoc.json). Each query is provided in three forms — Moroccan Darija, Modern Standard Arabic (MSA), and English — and is linked to one or more gold evidence articles requiring multi-hop reasoning across the statutory citation graph. The benchmark is designed to evaluate retrieval systems on Arabic morphological ambiguity, hidden definitional cross-references, and hierarchical document structure.