用本体构建知识图谱能显著提升RAG性能，且成本更低。
Ontology Learning and Knowledge Graph Construction: A Comparison of Approaches and Their Impact on RAG Performance
- 基于本体的知识图谱融合文本块信息，提升检索精度。
- 相比向量检索，性能大幅提升，接近顶尖框架水平。
- 来自关系数据库的本体构建更低成本，无需反复调用大模型。
检索增强生成（RAG）系统将大语言模型与外部知识结合，其性能高度依赖知识的表示方式。本研究探究不同知识图谱（KG）构建策略对RAG性能的影响。比较了标准向量RAG、GraphRAG，以及从关系数据库或文本语料中提取本体构建的KG的检索效果。结果表明，基于本体引导的KG融合文本块信息后，性能可与当前最优框架比肩，显著优于向量检索基线。此外，来自关系数据库的本体构建在性能上与文本提取方法相当，且具有双重优势：仅需一次性的本体学习过程，大幅降低大模型使用成本；避免了文本方法中复杂的本体合并问题。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) systems combine Large Language Models (LLMs) with external knowledge, and their performance depends heavily on how that knowledge is represented. This study investigates how different Knowledge Graph (KG) construction strategies influence RAG performance. We compare a variety of approaches: standard vector-based RAG, GraphRAG, and retrieval over KGs built from ontologies derived either from relational databases or textual corpora. Results show that ontology-guided KGs incorporating chunk information achieve competitive performance with state-of-the-art frameworks, substantially outperforming vector retrieval baselines. Moreover, the findings reveal that ontology-guided KGs built from relational databases perform competitively to ones built with ontologies extracted from text, with the benefit of offering a dual advantage: they require a one-time-only ontology learning process, substantially reducing LLM usage costs; and avoid the complexity of ontology merging inherent to text-based approaches.
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。