Using Large Language Models and Knowledge Graphs to Improve the Interpretability of Machine Learning Models in Manufacturing

2026-04-20 · Source: cs.AI updates on arXiv.org · Field: Technology & Digital — Artificial Intelligence & Machine Learning, AI in Manufacturing · Depth: Expert, quick

Summary

A novel method enhances the interpretability of Machine Learning (ML) models in manufacturing by integrating Large Language Models (LLMs) with Knowledge Graphs (KGs). This approach stores domain-specific data, ML results, and their explanations within a KG, creating a structured link between domain knowledge and ML insights. A selective retrieval method extracts relevant triplets from the KG, which an LLM then processes to generate user-friendly explanations of ML outcomes. The method was evaluated in a manufacturing environment using 33 questions from the XAI Question Bank, including complex, tailored queries. Quantitative metrics like accuracy and consistency, alongside qualitative measures such as clarity and usefulness, were used to analyze responses, demonstrating the approach's effectiveness in real-world manufacturing scenarios for improved decision-making.

Key takeaway

For Machine Learning Engineers seeking to improve model interpretability in industrial settings, integrating LLMs with Knowledge Graphs offers a robust solution. This method provides context-rich, user-friendly explanations for ML results, directly supporting better decision-making in manufacturing processes. You should consider structuring your domain knowledge into a KG to enhance the transparency and utility of your ML deployments.

Key insights

Combining LLMs and KGs can generate user-friendly, context-aware explanations for ML model predictions.

Principles

• Structured domain knowledge improves ML interpretability.
• LLMs can dynamically access KGs for explanations.

Method

Store domain data, ML results, and explanations in a KG. Extract relevant KG triplets using selective retrieval. Process triplets with an LLM to generate user-friendly explanations.

In practice

• Apply to manufacturing for better decision-making.
• Use XAI Question Bank for evaluation.

Topics

• Large Language Models
• Knowledge Graphs
• Explainable AI
• Machine Learning Interpretability
• Manufacturing Environment

Best for: AI Scientist, Machine Learning Engineer, Research Scientist

Related on AIssential

• Using Large Language Models and Knowledge Graphs to Improve the Interpretability of Machine Learning Models in Manufacturing — Integrating KGs with LLMs can significantly improve ML model interpretability by providing structured, context-rich explanations.
• Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrieval — Integrating graphs with LLMs enhances reasoning, retrieval, and decision-making by combining structured knowledge with semantic understanding.
• Construction of Knowledge Graph based on Language Model — PLMs significantly enhance Knowledge Graph construction by automating entity and relation extraction from text.
• Feature Engineering with LLMs: Techniques & Python Examples — LLMs automate semantic feature engineering, transforming raw data into context-rich representations for improved ML performance.
• IEEE Transactions on Artificial Intelligence, Volume 7, Issue 2, February 2026 — The volume showcases diverse AI advancements, from LLM applications in autonomous driving to specialized models for protein language processing.
• Building Trust in the Skies: A Knowledge-Grounded LLM-based Framework for Aviation Safety — Combining LLMs with dynamically updated Knowledge Graphs enhances trustworthiness and verifiability in safety-critical aviation analytics.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by cs.AI updates on arXiv.org.