Knowledge Graph Analysis of Legal Understanding and Violations in LLMs

TL;DR

This paper evaluates how well large language models understand and interpret complex legal laws, especially in sensitive areas like biological weapons, using knowledge graphs and retrieval-augmented generation to identify strengths and vulnerabilities.

Contribution

It introduces a novel methodology combining knowledge graphs and RAG to systematically assess LLMs' legal understanding and safety in sensitive legal contexts.

Findings

LLMs show limitations in legal reasoning and safety mechanisms.

Structured evaluation reveals vulnerabilities in generating unsafe outputs.

Proposes safety enhancements and legal reasoning improvements for LLMs.

Abstract

The rise of Large Language Models (LLMs) offers transformative potential for interpreting complex legal frameworks, such as Title 18 Section 175 of the US Code, which governs biological weapons. These systems hold promise for advancing legal analysis and compliance monitoring in sensitive domains. However, this capability comes with a troubling contradiction: while LLMs can analyze and interpret laws, they also demonstrate alarming vulnerabilities in generating unsafe outputs, such as actionable steps for bioweapon creation, despite their safeguards. To address this challenge, we propose a methodology that integrates knowledge graph construction with Retrieval-Augmented Generation (RAG) to systematically evaluate LLMs' understanding of this law, their capacity to assess legal intent (mens rea), and their potential for unsafe applications. Through structured experiments, we assess their accuracy in identifying legal violations, generating prohibited instructions, and detecting unlawful intent in bioweapons-related scenarios. Our findings reveal significant limitations in LLMs' reasoning and safety mechanisms, but they also point the way forward. By combining enhanced safety protocols with more robust legal reasoning frameworks, this research lays the groundwork for developing LLMs that can ethically and securely assist in sensitive legal domains - ensuring they act as protectors of the law rather than inadvertent enablers of its violation.