2024/09/09 by Tuba Gokhan, Kexin Wang, Gokhan, Tuba +5 · 1 citation
Computer Science · Social Sciences · #Access Control and Trust #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #Computational Engineering #Emerging Technologies (cs.ET) #FOS: Computer and information sciences #Finance #Hate Speech and Cyberbullying Detection #Information Retrieval (cs.IR) #Privacy, Security, and Data Protection #and Science (cs.CE)
paper · doi:10.48550/arxiv.2409.05677
openalex publication_date 2024/09/09 · openalex created_date 2024/10/22 · openalex updated_date 2026/07/28
Regulatory documents, issued by governmental regulatory bodies, establish rules, guidelines, and standards that organizations must adhere to for legal compliance. These documents, characterized by their length, complexity and frequent updates, are challenging to interpret, requiring significant allocation of time and expertise on the part of organizations to ensure ongoing compliance. Regulatory Natural Language Processing (RegNLP) is a multidisciplinary field aimed at simplifying access to and interpretation of regulatory rules and obligations. We introduce a task of generating question-passages pairs, where questions are automatically created and paired with relevant regulatory passages, facilitating the development of regulatory question-answering systems. We create the ObliQA dataset, containing 27,869 questions derived from the collection of Abu Dhabi Global Markets (ADGM) financial regulation documents, design a baseline Regulatory Information Retrieval and Answer Generation (RIRAG) system and evaluate it with RePASs, a novel evaluation metric that tests whether generated answers accurately capture all relevant obligations while avoiding contradictions.