@inproceedings{cheng-etal-2024-shield,
    title = "{SHIELD}: {LLM}-Driven Schema Induction for Predictive Analytics in {EV} Battery Supply Chain Disruptions",
    author = "Cheng, Zhi-Qi  and
      Dong, Yifei  and
      Shi, Aike  and
      Liu, Wei  and
      Hu, Yuzhi  and
      O{'}Connor, Jason  and
      Hauptmann, Alexander G  and
      Whitefoot, Kate",
    editor = "Dernoncourt, Franck  and
      Preo{\c{t}}iuc-Pietro, Daniel  and
      Shimorina, Anastasia",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: Industry Track",
    month = nov,
    year = "2024",
    address = "Miami, Florida, US",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Add-Cong-Liu-Florida-Atlantic-University-author-id/2024.emnlp-industry.24/",
    doi = "10.18653/v1/2024.emnlp-industry.24",
    pages = "303--333",
    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."
}