Knowledge Graph-Enhanced LLMs for Supply Chain Intelligence: Automating Network Visibility Through Public Data Mining
Shikha Duttyal · Technix International Journal for Engineering Research · 2025
Knowledge Graph integration with Large Language Models presents a novel framework for automated supply chain intelligence through public data mining. This innovation overcomes traditional visibility limitations by leveraging unstructured information sources rather than relying exclusively on stakeholder data sharing. Advanced LLMs systematically extract supply chain entities and relationships from news reports, regulatory filings, and trade databases, organizing these facts into semantically rich Knowledge Graphs that provide comprehensive, machine-readable network representations. The resulting system enables dynamic, real-time mapping of complex global supply chains, supporting enhanced risk monitoring, resilience planning, and regulatory compliance efforts. Case examples across multiple industries illustrate practical applications, while evaluation metrics confirm improved accuracy over existing methods. Ethical and practical challenges remain alongside promising directions for improving extraction reliability and model performance, offering a scalable solution to persistent supply network opacity without requiring direct data input from involved companies.