Entity Linking using LLMs for Automated Product Carbon Footprint Estimation

2025-02-11

AI Summary

To address the challenge of automatically aligning Bill-of-Materials (BOM) components with Life Cycle Assessment (LCA) database entries in manufacturing carbon footprint accounting, this paper proposes the first end-to-end entity alignment method leveraging large language models (LLMs). The approach requires no manual annotation or rule-based templates; instead, it employs domain-aware prompt engineering, zero-shot semantic expansion, and vector retrieval to achieve high-precision mapping from BOM component names to LCA database entries. Its core innovation lies in deeply integrating LLMs into cross-domain terminology understanding and semantic similarity computation, significantly enhancing robustness under heterogeneous naming conventions. Evaluated on a real-world manufacturing BOM dataset, the method achieves an 89.3% link accuracy—32 percentage points higher than conventional methods—substantially reducing environmental data preparation costs and providing a scalable technical pathway for automated life cycle assessment.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Natural Language Processing: Information Extraction

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Growing concerns about climate change and sustainability are driving manufacturers to take significant steps toward reducing their carbon footprints. For these manufacturers, a first step towards this goal is to identify the environmental impact of the individual components of their products. We propose a system leveraging large language models (LLMs) to automatically map components from manufacturer Bills of Materials (BOMs) to Life Cycle Assessment (LCA) database entries by using LLMs to expand on available component information. Our approach reduces the need for manual data processing, paving the way for more accessible sustainability practices.

Problem

• Automate carbon footprint estimation
• Map components to LCA databases
• Reduce manual data processing needs

Innovation

• LLMs for entity linking
• Automated BOM to LCA mapping
• Reduced manual data processing