Year: 2026
Type: article
Abstract: This article analyses the practical implementation of a local large language model (Ministral 3B) supported by Retrieval-Augmented Generation (RAG) in dangerous goods logistics, with a focus on verifying ADR exemptions, reducing AI hallucinations, and maintaining data privacy. The study uses a critical literature review and an empirical case study. The model was tested locally under stringent parameter constraints, including temperature 0.1 and strict system instructions. The analysis covered one comprehensive query concerning the transport of goods packed in limited quantities (LQ). Model responses were assessed for substantive compliance with ADR regulations and the commentary of a Dangerous Goods Safety Adviser (DGSA), comparing outputs generated with and without RAG. The results indicate that the RAG-supported model synthesized legal information more accurately and substantially reduced hallucinations in the analysed case compared with the raw model, which fabricated non-existent legal structures. However, conservative parameter settings may cause the omission of minor technical nuances. The findings suggest that local LLMs combined with RAG can support DGSA work, but only as auxiliary tools subject to continuous expert verification.
DOI: 10.25312/ziwgib.888
Author: Damian Kociemba
Language: English
Subfield: Law
Field: Social Sciences
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W7235197276
