Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Supply Chain Network Extraction and Entity Classification Leveraging Large Language Models

Tong Liu, Hadi Meidani

TL;DR

A novel approach that leverages LLMs to extract and process raw textual information from publicly available sources to construct a comprehensive supply chain graph is proposed and a fine-tuned LLM model is fine-tuned that enhances entity classification and understanding of supply chain networks.

Abstract

Supply chain networks are critical to the operational efficiency of industries, yet their increasing complexity presents significant challenges in mapping relationships and identifying the roles of various entities. Traditional methods for constructing supply chain networks rely heavily on structured datasets and manual data collection, limiting their scope and efficiency. In contrast, recent advancements in Natural Language Processing (NLP) and large language models (LLMs) offer new opportunities for discovering and analyzing supply chain networks using unstructured text data. This paper proposes a novel approach that leverages LLMs to extract and process raw textual information from publicly available sources to construct a comprehensive supply chain graph. We focus on the civil engineering sector as a case study, demonstrating how LLMs can uncover hidden relationships among companies, projects, and other entities. Additionally, we fine-tune an LLM to classify entities within the supply chain graph, providing detailed insights into their roles and relationships. The results show that domain-specific fine-tuning improves classification accuracy, highlighting the potential of LLMs for industry-specific supply chain analysis. Our contributions include the development of a supply chain graph for the civil engineering sector, as well as a fine-tuned LLM model that enhances entity classification and understanding of supply chain networks.

Supply Chain Network Extraction and Entity Classification Leveraging Large Language Models

TL;DR

A novel approach that leverages LLMs to extract and process raw textual information from publicly available sources to construct a comprehensive supply chain graph is proposed and a fine-tuned LLM model is fine-tuned that enhances entity classification and understanding of supply chain networks.

Abstract

Supply chain networks are critical to the operational efficiency of industries, yet their increasing complexity presents significant challenges in mapping relationships and identifying the roles of various entities. Traditional methods for constructing supply chain networks rely heavily on structured datasets and manual data collection, limiting their scope and efficiency. In contrast, recent advancements in Natural Language Processing (NLP) and large language models (LLMs) offer new opportunities for discovering and analyzing supply chain networks using unstructured text data. This paper proposes a novel approach that leverages LLMs to extract and process raw textual information from publicly available sources to construct a comprehensive supply chain graph. We focus on the civil engineering sector as a case study, demonstrating how LLMs can uncover hidden relationships among companies, projects, and other entities. Additionally, we fine-tune an LLM to classify entities within the supply chain graph, providing detailed insights into their roles and relationships. The results show that domain-specific fine-tuning improves classification accuracy, highlighting the potential of LLMs for industry-specific supply chain analysis. Our contributions include the development of a supply chain graph for the civil engineering sector, as well as a fine-tuned LLM model that enhances entity classification and understanding of supply chain networks.

Paper Structure

This paper contains 12 sections, 2 equations, 4 figures, 2 tables.

Table of Contents

  1. Introduction
  2. Proposed Methodology
  3. Data collection
  4. Article Entity Summarization and Extraction
  5. Supply Chain Network Construction
  6. Supply Chain Entity Classification
  7. Numerical Experiments
  8. Experiment Setup
  9. Experiment Result
  10. Supply Chain Network Construction
  11. Entity Classification
  12. Conclusion and Discussion

Figures (4)

  • Figure 1: Workflow for supply chain graph construction using LLMs. The process begins with keyword queue construction, followed by information retrieval and text preprocessing. After fine-tuning, the LLM is used for entity classification and question answering, ultimately generating the supply chain network
  • Figure 2: Constructed supply chain network graph. Each node in the graph represents a distinct entity in the civil engineering industry.
  • Figure 3: Distribution of the categories in the supply chain network graph. The labelled data will be used in the fine-tuning LLMs
  • Figure 4: Subgraph constructed from the single keyword. We take AECOM and Bechtel as two examples, for each grpah, we sampled 50 neighbors and related entity to visualize.