HELP: HyperNode Expansion and Logical Path-Guided Evidence Localization for Accurate and Efficient GraphRAG
This addresses the trade-off between accuracy and efficiency in GraphRAG for knowledge-intensive tasks, offering a practical improvement for applications requiring reliable multi-hop reasoning.
The paper tackles the problem of balancing accuracy and efficiency in Graph-based Retrieval-Augmented Generation (GraphRAG) for multi-hop reasoning by proposing the HELP framework, which achieves competitive performance on QA benchmarks and up to a 28.8x speedup over baselines.
Large Language Models (LLMs) often struggle with inherent knowledge boundaries and hallucinations, limiting their reliability in knowledge-intensive tasks. While Retrieval-Augmented Generation (RAG) mitigates these issues, it frequently overlooks structural interdependencies essential for multi-hop reasoning. Graph-based RAG approaches attempt to bridge this gap, yet they typically face trade-offs between accuracy and efficiency due to challenges such as costly graph traversals and semantic noise in LLM-generated summaries. In this paper, we propose HyperNode Expansion and Logical Path-Guided Evidence Localization strategies for GraphRAG (HELP), a novel framework designed to balance accuracy with practical efficiency through two core strategies: 1) HyperNode Expansion, which iteratively chains knowledge triplets into coherent reasoning paths abstracted as HyperNodes to capture complex structural dependencies and ensure retrieval accuracy; and 2) Logical Path-Guided Evidence Localization, which leverages precomputed graph-text correlations to map these paths directly to the corpus for superior efficiency. HELP avoids expensive random walks and semantic distortion, preserving knowledge integrity while drastically reducing retrieval latency. Extensive experiments demonstrate that HELP achieves competitive performance across multiple simple and multi-hop QA benchmarks and up to a 28.8$\times$ speedup over leading Graph-based RAG baselines.