Scholarlink

This article introduces a framework for knowledge base question answering using a Large Language Model (LLM). The framework transforms natural language queries into structured forms, enhancing accuracy and efficiency. Advanced fine-tuning techniques refine the LLM’s NLP capabilities. The framework also includes a novel knowledge matching approach combining coarse and fine granularity, leveraging character and word vector similarities with semantic analysis. Experimental results show high accuracy and efficiency in retrieving answers, offering a robust solution for information retrieval.

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

LLM-KBQA: A Knowledge Base Question Answering Framework Based on Large Language Models

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Ziliang Li,
  • Haoliang Cui,
  • Wen Zhang,
  • Maosen Wang,
  • Shaozhang Niu

摘要

This article introduces a framework for knowledge base question answering using a Large Language Model (LLM). The framework transforms natural language queries into structured forms, enhancing accuracy and efficiency. Advanced fine-tuning techniques refine the LLM’s NLP capabilities. The framework also includes a novel knowledge matching approach combining coarse and fine granularity, leveraging character and word vector similarities with semantic analysis. Experimental results show high accuracy and efficiency in retrieving answers, offering a robust solution for information retrieval.