🤖 AI Summary
Small organizations and startups often lack access to legal expertise, hindering their ability to interpret and comply with regulatory requirements. Method: This work proposes a lightweight, low-supervision legal text structuring approach that integrates textual entailment recognition, in-context learning, and domain-specific meta-model-driven Python class generation to automatically extract semantic legal metadata and explicitly encode logical relationships—yielding verifiable, executable compliance representations. Contribution/Results: The method avoids reliance on large-scale annotated datasets, thereby enhancing cross-regulation generalizability; crucially, it directly maps legal provisions to runnable code. Evaluated on data breach notification laws across 13 U.S. states, the generated representations pass 89.4% of test cases, achieving 82.2% precision and 88.7% recall.
📝 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.