ARCCS: An Automated Regulatory Compliance Checking System
Open-source ARCCS turns regulations into atomic requirements and detects EU procurement violations with 98.8 percent accuracy.
ARCCS is an open-source, regulation-agnostic agentic Legal NLP system that splits regulatory text into atomic requirements and checks a target document against them using retrieved evidence, confidence scores, and justifications. It is designed to work without a fixed regulatory template. LLM judges found its GDPR policy decisions and justifications legally and evidentially consistent in up to 96.67 percent of assessed cases. On an EU public-procurement benchmark of more than 1,200 rule checks, it reached 98.8 percent violation-detection accuracy.
- Decomposes regulations into atomic, traceable requirements with evidence.
- GDPR decisions judged consistent in up to 96.67 percent of cases.
- 98.8 percent violation detection on more than 1,200 procurement checks.
- Claimed as the first fully open-source end-to-end compliance checker.
- Countries
- European Union
From the original article
1 min read at arxiv.orgRegulatory 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.
By Giorgos Filandrianos · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.