HalluGraph: Auditable Hallucination Detection for Legal RAG Systems via Knowledge Graph Alignment

Valentin NOËL, Elimane Yassine SEIDOU, Charly Ken CAPO-CHICHI, Ghanem AMARI

Keywords: Legal RAG, Hallucination Detection, Accountability, Explainability, Knowledge Graphs, Auditable AI, Professional Responsibility

Paper Type: Short papers / work-in-progress

TL;DR: HalluGraph detects hallucinations in legal RAG via knowledge graph alignment, providing bounded metrics and a transparent audit trail for high-stakes applications.

Abstract: Legal AI systems powered by retrieval-augmented generation (RAG) face a critical accountability challenge: when an AI assistant cites case law, statutes, or contractual clauses, practitioners need verifiable guarantees that generated text faithfully represents source documents. Existing hallucination detectors rely on semantic similarity metrics that tolerate entity substitutions, a dangerous failure mode when confusing parties, dates, or legal provisions can have material consequences. We introduce HalluGraph, a graph-theoretic framework that quantifies hallucinations through structural alignment between knowledge graphs extracted from context, query, and response. Our approach produces bounded, interpretable metrics decomposed into \textit{Entity Grounding} (EG), measuring whether entities in the response appear in source documents, and \textit{Relation Preservation} (RP), verifying that asserted relationships are supported by context. On structured control documents, HalluGraph achieves near-perfect discrimination ($>$400 words, $>$20 entities), HalluGraph achieves $AUC = 0.979$, while maintaining robust performance ($AUC \approx 0.89$) on challenging generative legal task, consistently outperforming semantic similarity baselines. The framework provides the transparency and traceability required for high-stakes legal applications, enabling full audit trails from generated assertions back to source passages. To facilitate reproducibility, our code, dataset, and an interactive demo are publicly available at: \url{https://vcnoel.github.io/hallugraph-demo/}.

Submission Number: 47