Enhancing Supply Chain Risk Management with LLMs: An Application for Natural Hazard Monitoring

Abstract

Abstract Impacts of natural hazards on supply chains can be devastating, especially given the increase in their frequency and intensity. For larger and geographically dispersed supply chains, it is critical to monitor supply chain nodes for natural hazard risk and take early actions to mitigate their impact. However, this requires an automated system that is capable of retrieving and analyzing dynamic information specific to these locations for rapid risk assessment. This paper proposes an automated risk identification and assessment system for natural hazards using Large Language Models (LLMs) and news data. First, critical risk features for natural hazard risk assessment are identified from the literature. Then, news articles about natural hazards that occurred in supply nodes are retrieved, and risk feature information is extracted by four LLMs (Llama3.1-8B, Gemma3-12B, DeepSeek-R1-14B, Phi4-14B) using three prompting strategies (zero-shot, few-shot, and chain-of-thought). A bicycle case study that involves a global supply chain network is applied to demonstrate the effectiveness of the proposed system. The performance of LLMs is evaluated for i) correctness by human evaluators, and ii) contextual similarity by using Bidirectional Encoder Representations from Transformers Score (BERTScore). Results show that Llama3.1-8B and Phi4-14B have strong potential for automated risk assessment, achieving higher scores in both human evaluation and BERTScore. However, DeepSeek-R1-14B resulted in the lowest performance among the tested LLMs. Furthermore, hazards impacting a wider region reduce LLM performance due to complex links between location and risk features.