Skip to content
GCC AI Research

RIRAG: Regulatory Information Retrieval and Answer Generation

arXiv · · Notable

NLP LLM Arabic AI Research Finance

Summary

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.

Keywords

RegNLP · regulatory documents · question answering · dataset · ADGM

Read original article →

Get the weekly digest

Top AI stories from the GCC region, every week.