大语言模型与知识图谱在问答系统中的融合： 综合分析与未来机遇

Large Language Models Meet Knowledge Graphs for Question Answering: Synthesis and Opportunities

May 26, 2025

作者: Chuangtao Ma, Yongrui Chen, Tianxing Wu, Arijit Khan, Haofen Wang

cs.AI

摘要

大型语言模型（LLMs）在问答（QA）任务中展现了卓越的性能，这得益于其在自然语言理解和生成方面的强大能力。然而，基于LLM的QA在处理复杂QA任务时仍面临挑战，包括推理能力不足、知识陈旧以及产生幻觉等问题。近期多项研究尝试将LLMs与知识图谱（KGs）结合用于QA，以应对上述挑战。在本综述中，我们提出了一种新的结构化分类法，根据QA的类别以及KG在与LLMs整合时的角色，对LLMs与KGs结合用于QA的方法进行了分类。我们系统地调研了LLMs与KGs结合用于QA的最新进展，并从优势、局限性和KG需求等方面对这些方法进行了比较与分析。随后，我们将这些方法与QA任务对齐，并探讨了它们如何解决不同复杂QA的主要挑战。最后，我们总结了相关进展、评估指标和基准数据集，并指出了开放性的挑战与机遇。

English

Large language models (LLMs) have demonstrated remarkable performance on question-answering (QA) tasks because of their superior capabilities in natural language understanding and generation. However, LLM-based QA struggles with complex QA tasks due to poor reasoning capacity, outdated knowledge, and hallucinations. Several recent works synthesize LLMs and knowledge graphs (KGs) for QA to address the above challenges. In this survey, we propose a new structured taxonomy that categorizes the methodology of synthesizing LLMs and KGs for QA according to the categories of QA and the KG's role when integrating with LLMs. We systematically survey state-of-the-art advances in synthesizing LLMs and KGs for QA and compare and analyze these approaches in terms of strength, limitations, and KG requirements. We then align the approaches with QA and discuss how these approaches address the main challenges of different complex QA. Finally, we summarize the advancements, evaluation metrics, and benchmark datasets and highlight open challenges and opportunities.