Legal Requirements Translation from Law

TL;DR

This paper presents a novel approach using textual entailment and in-context learning to automatically extract and represent legal requirements from complex legal texts as executable Python code, improving automation and generalization.

Contribution

It introduces a Python-based canonical representation for legal texts that captures metadata and interrelationships, reducing reliance on manual labeling and enhancing applicability to unseen legislation.

Findings

Achieved 89.4% pass rate on test cases

Precision of 82.2%, recall of 88.7%

Effective on 13 U.S. state data breach laws

Abstract

Software systems must comply with legal regulations, which is a resource-intensive task, particularly for small organizations and startups lacking dedicated legal expertise. Extracting metadata from regulations to elicit legal requirements for software is a critical step to ensure compliance. However, it is a cumbersome task due to the length and complex nature of legal text. Although prior work has pursued automated methods for extracting structural and semantic metadata from legal text, key limitations remain: they do not consider the interplay and interrelationships among attributes associated with these metadata types, and they rely on manual labeling or heuristic-driven machine learning, which does not generalize well to new documents. In this paper, we introduce an approach based on textual entailment and in-context learning for automatically generating a canonical representation of legal text, encodable and executable as Python code. Our representation is instantiated from a manually designed Python class structure that serves as a domain-specific metamodel, capturing both structural and semantic legal metadata and their interrelationships. This design choice reduces the need for large, manually labeled datasets and enhances applicability to unseen legislation. We evaluate our approach on 13 U.S. state data breach notification laws, demonstrating that our generated representations pass approximately 89.4% of test cases and achieve a precision and recall of 82.2 and 88.7, respectively.