Extracting Supply Chain Information From News Articles Using Large Language Models: A Fully Automatic Approach

Supply chain mapping is crucial for global companies to identify and mitigate potential risks. Although natural language processing techniques are analyzed to extract supply chain maps from textual sources to automate the process, they require extensive manual annotation of training data, limiting the scalability and efficiency of these approaches. This study addresses this limitation by exploring the use of large language models to automate supply chain mapping, specifically by investigating their potential for generating synthetic training data and improving relation classification. The performance of these synthetic datasets is compared with those of manually annotated datasets. Experimental results demonstrate that synthetic data can outperform manual data, particularly when manual data is scarce. To demonstrate its practical applicability, the developed method is applied to generate a supply chain map from mining-related news articles. The resulting visualization for mining-related industries highlights the method’s effectiveness in automated, real-time mapping using publicly available information, enabling the rapid identification of supply network changes. This study contributes to the supply chain management and natural language processing fields by advancing sophisticated, AI-driven supply chain analysis tools.