SHIELD: LLM-Driven Schema Induction for Predictive Analytics in EV Battery Supply Chain Disruptions

TL;DR

SHIELD is a novel system that combines large language models, schema learning, and graph neural networks to improve predictive analytics for EV battery supply chain disruptions, outperforming existing methods.

Contribution

The paper introduces SHIELD, a comprehensive framework integrating LLM-driven schema induction, event extraction, similarity matching, and GCNs with expert feedback for better disruption prediction.

Findings

SHIELD outperforms baseline GCNs and LLM+prompt methods in disruption prediction.

The system effectively combines LLMs with domain expertise for supply chain risk assessment.

Evaluated on over 12,000 paragraphs from 365 sources, demonstrating robustness.

Abstract

The electric vehicle (EV) battery supply chain's vulnerability to disruptions necessitates advanced predictive analytics. We present SHIELD (Schema-based Hierarchical Induction for EV supply chain Disruption), a system integrating Large Language Models (LLMs) with domain expertise for EV battery supply chain risk assessment. SHIELD combines: (1) LLM-driven schema learning to construct a comprehensive knowledge library, (2) a disruption analysis system utilizing fine-tuned language models for event extraction, multi-dimensional similarity matching for schema matching, and Graph Convolutional Networks (GCNs) with logical constraints for prediction, and (3) an interactive interface for visualizing results and incorporating expert feedback to enhance decision-making. Evaluated on 12,070 paragraphs from 365 sources (2022-2023), SHIELD outperforms baseline GCNs and LLM+prompt methods (e.g., GPT-4o) in disruption prediction. These results demonstrate SHIELD's effectiveness in combining LLM capabilities with domain expertise for enhanced supply chain risk assessment.