A Graph-based RAG for Energy Efficiency Question Answering

2025-11-03

AI Summary

Large language models (LLMs) exhibit insufficient domain-specific accuracy and interpretability in multilingual question answering for energy efficiency (EE). Method: This paper proposes a graph-enhanced retrieval-augmented generation (Graph-RAG) framework that automatically constructs a domain-specific knowledge graph from multilingual energy documents, integrating graph traversal-based reasoning with RAG to enable cross-lingual semantic alignment and structured inference. Contribution/Results: The framework embeds the logical interpretability of knowledge graphs into the RAG pipeline, supporting automated policy/guideline modeling and multi-hop QA. Evaluated via RAGAs and expert validation, the system achieves an overall accuracy of 75.2±2.7%, 81.0±4.1% on general EE questions, and incurs only a 4.4% performance degradation across languages—demonstrating substantial improvements in LLM robustness and adaptability within specialized domains.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Knowledge Representation and Reasoning: Knowledge Representation Languages
• Natural Language Processing: Question Answering

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

In this work, we investigate the use of Large Language Models (LLMs) within a graph-based Retrieval Augmented Generation (RAG) architecture for Energy Efficiency (EE) Question Answering. First, the system automatically extracts a Knowledge Graph (KG) from guidance and regulatory documents in the energy field. Then, the generated graph is navigated and reasoned upon to provide users with accurate answers in multiple languages. We implement a human-based validation using the RAGAs framework properties, a validation dataset comprising 101 question-answer pairs, and domain experts. Results confirm the potential of this architecture and identify its strengths and weaknesses. Validation results show how the system correctly answers in about three out of four of the cases (75.2 +- 2.7%), with higher results on questions related to more general EE answers (up to 81.0 +- 4.1%), and featuring promising multilingual abilities (4.4% accuracy loss due to translation).

Problem

• Developing graph-based RAG for energy efficiency question answering
• Extracting knowledge graphs from energy regulatory documents automatically
• Providing accurate multilingual answers through graph navigation and reasoning

Innovation

• Graph-based RAG architecture for energy efficiency QA
• Automatic Knowledge Graph extraction from energy documents
• Multilingual reasoning over graphs for accurate answers