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

2026-04-17 · Source: Artificial Intelligence · Field: Technology & Digital — Artificial Intelligence & Machine Learning · Depth: Advanced, quick

Summary

A novel method enhances the interpretability of Machine Learning (ML) models in manufacturing by integrating Knowledge Graphs (KGs) with Large Language Models (LLMs). The approach stores domain-specific data, ML results, and explanations within a KG, creating structured links 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. This system was evaluated in a manufacturing setting using the XAI Question Bank, including complex, tailored questions. The evaluation analyzed 33 questions using quantitative metrics like accuracy and consistency, alongside qualitative measures such as clarity and usefulness, demonstrating its practical applicability for improved decision-making.

Key takeaway

For Research Scientists developing XAI solutions in industrial settings, this method offers a robust way to make complex ML models more transparent. You should consider integrating Knowledge Graphs with LLMs to provide dynamic, context-aware explanations, moving beyond static interpretations. This approach can significantly improve decision-making by offering clearer insights into model behavior and predictions within your specific domain.

Key insights

Integrating KGs with LLMs can significantly improve ML model interpretability by providing structured, context-rich explanations.

Principles

• Structured domain knowledge enhances ML explainability.
• LLMs can translate KG data into user-friendly explanations.

Method

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

In practice

• Apply KGs to contextualize ML outputs.
• Use LLMs to generate natural language explanations.
• Evaluate XAI with tailored, complex questions.

Topics

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

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

Related on AIssential

• Using Large Language Models and Knowledge Graphs to Improve the Interpretability of Machine Learning Models in Manufacturing — Combining LLMs and KGs can generate user-friendly, context-aware explanations for ML model predictions.
• 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.
• 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.
• Construction of Knowledge Graph based on Language Model — PLMs significantly enhance Knowledge Graph construction by automating entity and relation extraction from text.
• Reasoning Structure of Large Language Models — Evaluating Large Reasoning Models requires analyzing their internal logical flow, not just final accuracy or token count.
• Connecting the Dots with Context Graphs — Stephen Chin, Neo4j — Context graphs integrate LLMs with knowledge graphs to provide grounded, explainable, and auditable AI-driven decision-making by connecting disparate enterprise data.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Artificial Intelligence.