VizRAG：通过超图可视化增强检索增强生成
VizRAG: Enhancing Retrieval-Augmented Generation with Hypergraph Visualization
浏览论文内容
中文总结 AI 辅助
研究旨在增强检索增强生成，核心方法是通过视觉线索将超图感知整合到RAG系统中，引入VizRAG支持视觉超图结构感知，实验证明该方法显著优于基线，验证了超图可视化用于RAG系统的潜力。
中文摘要 AI 辅助
基于超图的RAG系统通过组织实体间复杂的n元原子事实超越了传统基于图的方法，而非仅依赖二元关系。尽管具有增强视觉能力的多模态大语言模型取得进展，但当前基于超图的RAG框架主要将知识检索和重建限制在单模态、以文本为中心的范式。为填补这一差距，我们通过视觉线索系统探索超图感知在RAG系统中的整合。通过将超图的视觉表示纳入RAG管道，我们引入了VizRAG，首个支持视觉超图结构感知的RAG系统。实验结果表明VizRAG显著优于强大的基线，验证了超图可视化作为RAG系统新方法的潜力。
英文摘要
Hypergraph-based RAG systems surpass traditional graph-based approaches by organizing complex n-ary atomic facts among entities, rather than relying solely on binary relationships. Despite the advancements in multimodal large language models (MLLMs) with enhanced visual capabilities, current hypergraph-based RAG frameworks predominantly restrict knowledge retrieval and reconstruction to a unimodal, text-centric paradigm. This limitation prevents them from fully leveraging the powerful visual perception capabilities of modern MLLMs. To address this gap, we systematically explore the integration of hypergraph awareness in RAG systems through visual cues. By incorporating visual representations of hypergraphs into the RAG pipeline, we introduce VizRAG, the first RAG system to support visual hypergraph structure awareness. Experimental results demonstrate that VizRAG significantly outperforms strong baselines, validating the promising potential of hypergraph visualization as a novel approach for RAG systems.
发表机构
- Southern University of Science and Technology（南方科技大学）
- Hong Kong University of Science and Technology（香港科技大学）
- Huawei Research（华为研究院）
- Beihang University（北京航空航天大学）
机构由 AI 辅助整理，请以论文原文为准。
