Scholarlink

Knowledge Graphs (KGs) are used extensively for medical applications where accuracy of information is a critical requirement, but accessing this information requires expertise typical not available to medical practitioners. Large Language Models (LLMs) offer an efficient way to answer questions using natural language, but have limitations in various tasks requiring reasoning capabilities. Responses of LLMs often contain erroneous answers and non-existent facts, which is a major problem, especially in medical applications. In this work, we propose a solution to this problem by making use of Linked Open Data as a source of reliable information. Specifically, we propose an approach that leverages LLMs in order to allow for automatic SPARQL query generation from natural language. The proposed method is used on an Attention Deficit Hyperactivity Disorder Knowledge Graph (ADHD KG) and results demonstrate the potential of the proposed approach.

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

Leveraging LLMs for Querying an Attention Deficit Hyperactivity Disorder Knowledge Graph

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Charalampos Doulaverakis,
  • Giannis Vassiliou,
  • Emmanuel Papadakis,
  • Sotiris Batsakis,
  • Haridimos Kondylakis,
  • Georgia Eirini Trouli,
  • Nikos Papadakis,
  • Grigoris Antoniou

摘要

Knowledge Graphs (KGs) are used extensively for medical applications where accuracy of information is a critical requirement, but accessing this information requires expertise typical not available to medical practitioners. Large Language Models (LLMs) offer an efficient way to answer questions using natural language, but have limitations in various tasks requiring reasoning capabilities. Responses of LLMs often contain erroneous answers and non-existent facts, which is a major problem, especially in medical applications. In this work, we propose a solution to this problem by making use of Linked Open Data as a source of reliable information. Specifically, we propose an approach that leverages LLMs in order to allow for automatic SPARQL query generation from natural language. The proposed method is used on an Attention Deficit Hyperactivity Disorder Knowledge Graph (ADHD KG) and results demonstrate the potential of the proposed approach.