Enhancing Legal Compliance and Regulation Analysis with Large Language Models
Shabnam Hassani
TL;DR
This paper tackles the gap between regulatory analysis and AI capability in the food-safety and GDPR domains by developing an LLM-based approach that classifies requirements-related provisions and automates regulatory compliance checking. The methodology combines a four-step automated classification pipeline with a three-step automated compliance-checking workflow, instantiated with BERT and GPT-3.5, and evaluated on SFCR/FSRG content and DPAs. Empirical results show competitive accuracy for classification and substantial improvements in paragraph-level compliance checking compared to sentence-level analysis, suggesting meaningful gains in efficiency and scalability for regulatory analysis. The study highlights the importance of context-rich processing (paragraphs) and outlines concrete future work to broaden jurisdictional coverage and involve experts, aiming to advance practical adoption in industry and policy domains.
Abstract
This research explores the application of Large Language Models (LLMs) for automating the extraction of requirement-related legal content in the food safety domain and checking legal compliance of regulatory artifacts. With Industry 4.0 revolutionizing the food industry and with the General Data Protection Regulation (GDPR) reshaping privacy policies and data processing agreements, there is a growing gap between regulatory analysis and recent technological advancements. This study aims to bridge this gap by leveraging LLMs, namely BERT and GPT models, to accurately classify legal provisions and automate compliance checks. Our findings demonstrate promising results, indicating LLMs' significant potential to enhance legal compliance and regulatory analysis efficiency, notably by reducing manual workload and improving accuracy within reasonable time and financial constraints.