将GeAR图检索增强生成扩展至百万级文档，验证其通用性。
Millions of $\text{GeAR}$-s: Extending GraphRAG to Millions of Documents
- 基于实体关系构建文档图谱，提升跨文档检索能力
- 在SIGIR 2025 LiveRAG挑战中验证百万文档场景下的性能
- 为图结构RAG提供可扩展范例，适合大规模知识系统开发者
近期研究探索了基于图的检索增强生成方法，利用从文档中提取的实体及其关系等结构化信息来提升检索效果。然而，这些方法通常针对特定任务（如多跳问答、查询聚焦摘要）设计，缺乏在更广泛数据集上的通用性证据。本文旨在适配最先进的图基RAG方案GeAR，探究其在SIGIR 2025 LiveRAG挑战中的表现与局限性，评估其在百万级文档场景下的适用性。
原文摘要 · Abstract (English)
Recent studies have explored graph-based approaches to retrieval-augmented generation, leveraging structured or semi-structured information -- such as entities and their relations extracted from documents -- to enhance retrieval. However, these methods are typically designed to address specific tasks, such as multi-hop question answering and query-focused summarisation, and therefore, there is limited evidence of their general applicability across broader datasets. In this paper, we aim to adapt a state-of-the-art graph-based RAG solution: $\text{GeAR}$ and explore its performance and limitations on the SIGIR 2025 LiveRAG Challenge.
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。