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

作者：Houda Khrouf, P. Fillastre, S. Correia · 年份：2026 · 研究领域：Computer Science

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.