Retrieval Augmented Generation-based Large Language Models for Bridging Transportation Cybersecurity Legal Knowledge Gaps

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Akbar, Khandakar Ashrafi, Uddin, Md Nahiyan, Khan, Latifur, Hockstad, Trayce, Rahman, Mizanur, Chowdhury, Mashrur, Thuraisingham, Bhavani
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916756414529536
author Akbar, Khandakar Ashrafi
Uddin, Md Nahiyan
Khan, Latifur
Hockstad, Trayce
Rahman, Mizanur
Chowdhury, Mashrur
Thuraisingham, Bhavani
author_facet Akbar, Khandakar Ashrafi
Uddin, Md Nahiyan
Khan, Latifur
Hockstad, Trayce
Rahman, Mizanur
Chowdhury, Mashrur
Thuraisingham, Bhavani
contents As connected and automated transportation systems evolve, there is a growing need for federal and state authorities to revise existing laws and develop new statutes to address emerging cybersecurity and data privacy challenges. This study introduces a Retrieval-Augmented Generation (RAG) based Large Language Model (LLM) framework designed to support policymakers by extracting relevant legal content and generating accurate, inquiry-specific responses. The framework focuses on reducing hallucinations in LLMs by using a curated set of domain-specific questions to guide response generation. By incorporating retrieval mechanisms, the system enhances the factual grounding and specificity of its outputs. Our analysis shows that the proposed RAG-based LLM outperforms leading commercial LLMs across four evaluation metrics: AlignScore, ParaScore, BERTScore, and ROUGE, demonstrating its effectiveness in producing reliable and context-aware legal insights. This approach offers a scalable, AI-driven method for legislative analysis, supporting efforts to update legal frameworks in line with advancements in transportation technologies.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18426
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Retrieval Augmented Generation-based Large Language Models for Bridging Transportation Cybersecurity Legal Knowledge Gaps
Akbar, Khandakar Ashrafi
Uddin, Md Nahiyan
Khan, Latifur
Hockstad, Trayce
Rahman, Mizanur
Chowdhury, Mashrur
Thuraisingham, Bhavani
Computation and Language
Artificial Intelligence
As connected and automated transportation systems evolve, there is a growing need for federal and state authorities to revise existing laws and develop new statutes to address emerging cybersecurity and data privacy challenges. This study introduces a Retrieval-Augmented Generation (RAG) based Large Language Model (LLM) framework designed to support policymakers by extracting relevant legal content and generating accurate, inquiry-specific responses. The framework focuses on reducing hallucinations in LLMs by using a curated set of domain-specific questions to guide response generation. By incorporating retrieval mechanisms, the system enhances the factual grounding and specificity of its outputs. Our analysis shows that the proposed RAG-based LLM outperforms leading commercial LLMs across four evaluation metrics: AlignScore, ParaScore, BERTScore, and ROUGE, demonstrating its effectiveness in producing reliable and context-aware legal insights. This approach offers a scalable, AI-driven method for legislative analysis, supporting efforts to update legal frameworks in line with advancements in transportation technologies.
title Retrieval Augmented Generation-based Large Language Models for Bridging Transportation Cybersecurity Legal Knowledge Gaps
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.18426