用超图结构提升知识抽取与检索，让RAG更准更快。

Optimizing Hypergraph-Based RAG: Toward Better Fact Extraction and Chunk Retrieval

• 用自洽提示优化大模型抽取复杂事实
• 超图上运行个性化PageRank，提升检索效率
• 适合需要精准知识推理的场景

GraphRAG通过图结构实现深度推理，但难以处理高阶关系。HyperGraphRAG采用超图表示以增强语义表达，虽提升了准确性，但仍依赖易出错的大模型抽取和低效的标准分块检索。本文提出通过自洽提示（self-consistency prompting）改进事实抽取，并在超图上使用个性化PageRank算法优化分块检索，显著提升了信息提取与召回效果。

原文摘要 · Abstract (English)

GraphRAG enables deeper reasoning by structuring knowledge as graphs but struggles with n-ary facts. HyperGraphRAG uses hypergraphs for richer semantics, improving accuracy, yet relies on error-prone LLM extraction and inefficient standard chunk retrieval. We address this by employing self-consistency prompting to improve the extraction, and Personalized PageRank algorithm over hypergraph to enhance chunk retrieval.

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。