用混合超图填补轻量GraphRAG的语义鸿沟，提升多跳推理效果。
EHRAG: Bridging Semantic Gaps in Lightweight GraphRAG via Hybrid Hypergraph Construction and Retrieval
- 构建结构与语义双通道超边，融合实体共现与嵌入聚类信息。
- 在4个数据集上超越现有基线，索引复杂度保持线性且无额外令牌开销。
- 适合需要高效精准医疗问答的轻量级RAG应用者。
基于图的检索增强生成（GraphRAG）通过将语料库构造成图来增强大语言模型的多跳推理能力。尽管近期轻量级方法通过命名实体识别（NER）降低了索引成本，但其仅依赖结构共现关系，难以捕捉分离实体间的潜在语义联系。为此，我们提出EHRAG，一种轻量级RAG框架，通过构建同时包含结构与语义关系的超图，并采用混合结构-语义检索机制。具体而言，EHRAG基于句子级共现构建结构超边，利用轻量实体提取；通过聚类实体文本嵌入构建语义超边，确保超图涵盖双重信息。检索阶段，采用主题感知打分与个性化PageRank（PPR）优化的结构-语义混合扩散，识别top-k相关文档。在4个数据集上的实验表明，EHRAG在保持线性索引复杂度和零令牌消耗的前提下，优于当前最优基线。代码已开源：https://github.com/yfsong00/EHRAG。
原文摘要 · Abstract (English)
Graph-based Retrieval-Augmented Generation (GraphRAG) enhances LLMs by structuring corpus into graphs to facilitate multi-hop reasoning. While recent lightweight approaches reduce indexing costs by leveraging Named Entity Recognition (NER), they rely strictly on structural co-occurrence, failing to capture latent semantic connections between disjoint entities. To address this, we propose EHRAG, a lightweight RAG framework that constructs a hypergraph capturing both structure and semantic level relationships, employing a hybrid structural-semantic retrieval mechanism. Specifically, EHRAG constructs structural hyperedges based on sentence-level co-occurrence with lightweight entity extraction and semantic hyperedges by clustering entity text embeddings, ensuring the hypergraph encompasses both structural and semantic information. For retrieval, EHRAG performs a structure-semantic hybrid diffusion with topic-aware scoring and personalized pagerank (PPR) refinement to identify the top-k relevant documents. Experiments on four datasets show that EHRAG outperforms state-of-the-art baselines while maintaining linear indexing complexity and zero token consumption for construction. Code is available at https://github.com/yfsong00/EHRAG.
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。