Saved in:
Bibliographic Details
Main Authors: Jha, Abha, Salinas, Abel, Morstatter, Fred
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.08593
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915612139192320
author Jha, Abha
Salinas, Abel
Morstatter, Fred
author_facet Jha, Abha
Salinas, Abel
Morstatter, Fred
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_08593
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Knowledge Graph Analysis of Legal Understanding and Violations in LLMs
Jha, Abha
Salinas, Abel
Morstatter, Fred
Computation and Language
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.
title Knowledge Graph Analysis of Legal Understanding and Violations in LLMs
topic Computation and Language
url https://arxiv.org/abs/2511.08593