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

2026/07/02 by Houda Khrouf, Pedro Fillastre, Sebastiao Correia
#cs.AI

paper · pdf

Abstract

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.

Related

• HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation
• E²GraphRAG: Streamlining Graph-based RAG for High Efficiency and Effectiveness
• Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation
• ChunkRAG: Novel LLM-Chunk Filtering Method for RAG Systems
• NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes