This paper introduces a Regulatory Knowledge Graph (RKG) for the Abu Dhabi Global Market (ADGM) regulations, constructed using language models and graph technologies. A portion of the regulations was manually tagged to train BERT-based models, which were then applied to the rest of the corpus. The resulting knowledge graph, stored in Neo4j, and code are open-sourced on GitHub to promote advancements in compliance automation.
Researchers introduce a new task for generating question-passage pairs to aid in developing regulatory question-answering (QA) systems. The ObliQA dataset, comprising 27,869 questions from Abu Dhabi Global Markets (ADGM) financial regulations, is presented. A baseline Regulatory Information Retrieval and Answer Generation (RIRAG) system is designed and evaluated using the RePASs metric.
ADGM and MBZUAI have signed an MoU to advance AI applications in financial regulatory compliance. The partnership will focus on developing regtech and suptech solutions, including an AI model to extract meaning from financial regulations. A key project is enhancing FSRA’s ‘Risk Analyser’ platform, which uses AI to provide insights on supervised firms. Why it matters: This collaboration signals a push towards AI-driven regulatory innovation in the UAE's financial sector, potentially improving efficiency and compliance.