Can Legislation Be Made Machine-Readable in PROLEG?

TL;DR

This work addresses the challenge of converting human-readable GDPR provisions into machine-executable rules by using PROLEG as the target formalism in a human-in-the-loop pipeline. It proposes a fixed composite prompt that jointly generates if–then rules and a PROLEG encoding, with expert validation to ensure doctrinal fidelity and executable reasoning. The paper provides a qualitative evaluation of the doctrinal fidelity, a curated GDPR Article 6 rule set, and end-to-end demonstration including failure modes in PROLEG execution. The results show that while the approach can recover much of the normative structure, significant structural and semantic fidelity issues remain, underscoring the need for improved prompting, hybrid architectures, and broader generalization to other regulations for scalable, auditable machine-readable legislation.

Abstract

The anticipated positive social impact of regulatory processes requires both the accuracy and efficiency of their application. Modern artificial intelligence technologies, including natural language processing and machine-assisted reasoning, hold great promise for addressing this challenge. We present a framework to address the challenge of tools for regulatory application, based on current state-of-the-art (SOTA) methods for natural language processing (large language models or LLMs) and formalization of legal reasoning (the legal representation system PROLEG). As an example, we focus on Article 6 of the European General Data Protection Regulation (GDPR). In our framework, a single LLM prompt simultaneously transforms legal text into if-then rules and a corresponding PROLEG encoding, which are then validated and refined by legal domain experts. The final output is an executable PROLEG program that can produce human-readable explanations for instances of GDPR decisions. We describe processes to support the end-to-end transformation of a segment of a regulatory document (Article 6 from GDPR), including the prompting frame to guide an LLM to "compile" natural language text to if-then rules, then to further "compile" the vetted if-then rules to PROLEG. Finally, we produce an instance that shows the PROLEG execution. We conclude by summarizing the value of this approach and note observed limitations with suggestions to further develop such technologies for capturing and deploying regulatory frameworks.

Figures (3)

• Figure 1: Network of explicit cross-references among GDPR Articles.
• Figure 2: Example of PROLEG block diagram.
• Figure 3: Overview of the GDPR to PROLEG conversion process.