Scholarlink

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 composed of 101 question-answer pairs, and some 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 ( \(75.2\pm 2.7\%\) ), with higher results on questions related to more general EE answers (up to \(81.0\pm 4.1\%\) ), and featuring promising multilingual abilities ( \(4.4\%\) accuracy loss due to translation).

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Graph-Based RAG for Energy Efficiency Question Answering

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Riccardo Campi,
  • Nicolò Oreste Pinciroli Vago,
  • Mathyas Giudici,
  • Pablo Barrachina Rodriguez-Guisado,
  • Marco Brambilla,
  • Piero Fraternali

摘要

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 composed of 101 question-answer pairs, and some 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 ( \(75.2\pm 2.7\%\) ), with higher results on questions related to more general EE answers (up to \(81.0\pm 4.1\%\) ), and featuring promising multilingual abilities ( \(4.4\%\) accuracy loss due to translation).