Problem
Research questions and friction points this paper is trying to address.
Regulatory compliance checking
Legal NLP
GDPR
violation detection
ARCCS: An Automated Regulatory Compliance Checking System
🤖 AI Summary
This study addresses the challenges of interpreting legal texts, the lack of evidential support in compliance determination, and the reliance on fixed templates by proposing the first fully open-source, end-to-end intelligent agent system for regulatory compliance. Built upon a large language model-driven agent architecture, the system atomizes regulations into traceable requirements, integrates information retrieval with evidence chain reasoning to assess document compliance, and generates audit-grade interpretable reports. A core contribution is its regulation-agnostic decoupled design, which supports structured regulations of arbitrary scale. Experimental results demonstrate that the system achieves a decision consistency of 96.67% in GDPR policy evaluation and a violation detection accuracy of 98.8% on an EU public procurement benchmark.
📝 Abstract
Regulatory compliance checking - deciding whether a target document satisfies the obligations of a regulation - requires interpreting dense legal text, identifying which provisions apply, and grounding each decision in explicit evidence. We present ARCCS, an end-to-end, automated, agentic, and regulation-agnostic Legal NLP system for compliance checking. ARCCS decomposes raw regulatory text into atomic, traceable requirements and evaluates a target document against them using retrieved evidence, confidence scores, and human-interpretable justifications. This design decouples compliance assessment from any fixed regulatory template or predefined rule set, enabling the pipeline to operate over regulations of varying size and structure. We evaluate ARCCS in two complementary settings. First, in a GDPR policy-document evaluation, LLM-based judges find its decisions and justifications legally and evidentially consistent in up to 96.67% of the assessed cases. Second, on an EU public-procurement benchmark comprising more than 1,200 individual rule checks, the system attains 98.8% accuracy in violation detection. ARCCS is, to our knowledge, the first fully open-source system for end-to-end regulatory compliance checking and auditable report generation.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Regulatory Compliance Checking
Legal NLP
Agentic System
Evidence Retrieval
Open-Source
🔎 Similar Papers
No similar papers found.
