对比三种知识图谱构建法，发现GraphRAG在问答推理上表现最佳。
Fusing Knowledge and Language: A Comparative Study of Knowledge Graph-Based Question Answering with LLMs
- 用spaCy、CoreNLP-OpenIE和GraphRAG提取三元组并接入LLM
- OpenIE覆盖最全，但GraphRAG推理能力最强
- 适合想提升复杂问题理解的开发者参考
知识图谱通过关系三元组结构化信息，近年来成为增强问答系统的新主流。传统检索增强生成（RAG）方法擅长从简短文本中提取事实与局部上下文，但在处理复杂长文本的主题性与整体理解时存在局限，需更深入分析文本与上下文。本文对三种基于开源技术构建知识图谱三元组并集成至大语言模型（LLM）的问答方法进行系统性对比：spaCy、Stanford CoreNLP-OpenIE与GraphRAG。通过分析其能力、发展状态及对LLM问答性能的影响，评估其有效性、可行性与适应性。实验表明，尽管OpenIE在三元组覆盖率上最优，但GraphRAG在推理能力方面表现更佳。论文最后讨论各方法优劣，并提出未来改进方向。
原文摘要 · Abstract (English)
Knowledge graphs, a powerful tool for structuring information through relational triplets, have recently become the new front-runner in enhancing question-answering systems. While traditional Retrieval Augmented Generation (RAG) approaches are proficient in fact-based and local context-based extraction from concise texts, they encounter limitations when addressing the thematic and holistic understanding of complex, extensive texts, requiring a deeper analysis of both text and context. This paper presents a comprehensive technical comparative study of three different methodologies for constructing knowledge graph triplets and integrating them with Large Language Models (LLMs) for question answering: spaCy, Stanford CoreNLP-OpenIE, and GraphRAG, all leveraging open source technologies. We evaluate the effectiveness, feasibility, and adaptability of these methods by analyzing their capabilities, state of development, and their impact on the performance of LLM-based question answering. Experimental results indicate that while OpenIE provides the most comprehensive coverage of triplets, GraphRAG demonstrates superior reasoning abilities among the three. We conclude with a discussion on the strengths and limitations of each method and provide insights into future directions for improving knowledge graph-based question answering.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。