arXiv AI By Jisoo Kim, Taeyoon Kwack, Jinwoo Jang, Woo Kyung Kim, Honguk Woo

Code-as-Auditor: Executable Compliance Reasoning via Regulation-to-Code

Read the original on arXiv AI →

Code-as-Auditor is an LLM-based framework that transforms regulatory information into formal checklists and executable decision trees, encoding rules as interpretable code. During inference, the model expands each checklist item into factual and counterfactual questions, guiding reasoning over case-specific evidence and potential violations. This pipeline moves from evidence identification to rule application and final decision-making, with a self‑verification loop that enhances logical consistency and traceability, leading to more accurate and evidence‑backed compliance evaluations in privacy and data protection scenarios.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI
Jul 7

From Regulation to Requirements: An Automated Requirement Derivation and Explanation Pipeline

arXiv:2607. 04448v1 Announce Type: cross Abstract: Ensuring software compliance with regulations such as the General Data Protection Regulation (GDPR) and the Artificial Intelligence Act (EU AI Act) poses a significant challenge, as requirements engineers must translate complex legal text into actionable software requirements - a process that remains largely manual and error-prone in practice.

By Pavithra PM Nair, Preethu Rose Anish
Hugging Face Trending Papers
5d ago

A decision-support system applied to Law: Reasoning and explainability of the decision

The paper presents a decision‑support framework for Law Enforcement Agencies that formalises EU regulations such as the Law Enforcement Directive and uses symbolic AI with SPARQL to reason over legal rules. It includes an algorithm that generates justifications for its conclusions and a decision‑tree method to identify additional information needed when reasoning is inconclusive. The framework emphasizes explainability to build user confidence in automated legal decisions.

Hugging Face Trending Papers
Aug 3

CTRAG: An In-Context Retrieval-based Framework for Automated Compliance Checking using LLMs

Trust is fundamental in modern regulatory ecosystems, and compliance checking plays a critical role in fostering that trust. Regulatory compliance verification is essential for businesses operating in highly controlled environments, as it ensures alignment with sector-specific guidelines across domains such as financial reporting, data privacy, and cybersecurity.