An Ontology-Driven Graph RAG for Legal Norms: A Structural, Temporal, and Deterministic Approach
This addresses the challenge of building trustworthy and explainable legal AI systems for legal professionals, though it is incremental as it builds on existing RAG and knowledge graph methods.
The paper tackled the problem of standard RAG systems being inadequate for legal norms due to their inability to handle hierarchical, temporal, and causal structures, resulting in unreliable answers; it introduced SAT-Graph RAG, an ontology-driven framework that models legal norms explicitly, and demonstrated through a case study on the Brazilian Constitution that it provides a verifiable, temporally-correct substrate for LLMs, drastically reducing factual errors.
Retrieval-Augmented Generation (RAG) systems in the legal domain face a critical challenge: standard, flat-text retrieval is blind to the hierarchical, diachronic, and causal structure of law, leading to anachronistic and unreliable answers. This paper introduces the Structure-Aware Temporal Graph RAG (SAT-Graph RAG), an ontology-driven framework designed to overcome these limitations by explicitly modeling the formal structure and diachronic nature of legal norms. We ground our knowledge graph in a formal, LRMoo-inspired model that distinguishes abstract legal Works from their versioned Expressions. We model temporal states as efficient aggregations that reuse the versioned expressions (CTVs) of unchanged components, and we reify legislative events as first-class Action nodes to make causality explicit and queryable. This structured backbone enables a unified, planner-guided query strategy that applies explicit policies to deterministically resolve complex requests for (i) point-in-time retrieval, (ii) hierarchical impact analysis, and (iii) auditable provenance reconstruction. Through a case study on the Brazilian Constitution, we demonstrate how this approach provides a verifiable, temporally-correct substrate for LLMs, enabling higher-order analytical capabilities while drastically reducing the risk of factual errors. The result is a practical framework for building more trustworthy and explainable legal AI systems.