LinearRAG：面向大规模语料库的线性图检索增强生成
LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora
AI总结：
本文提出LinearRAG框架，通过无关系的Tri-Graph层次图构建和两阶段检索策略，在不依赖关系抽取的情况下实现大规模语料库上可靠且经济的图检索增强生成，并在多个数据集上显著优于基线模型。
摘要：
检索增强生成（RAG）通过利用外部知识被广泛用于缓解大语言模型（LLM）的幻觉问题。虽然RAG对简单查询有效，但传统RAG系统在信息碎片化的大规模非结构化语料库上表现不佳。近期进展引入知识图谱来捕捉关系结构，从而为复杂的多跳推理任务实现更全面的检索。然而，现有的基于图的RAG（GraphRAG）方法依赖不稳定且成本高昂的关系抽取来构建图，常常产生带有错误或不一致关系的噪声图，从而降低检索质量。本文重新审视现有GraphRAG系统的流程，并提出LinearRAG（Linear Graph-based Retrieval-Augmented Generation），一个能够实现可靠图构建和精确段落检索的高效框架。具体而言，LinearRAG仅使用轻量级实体抽取和语义链接构建一个无关系的层次化图，称为Tri-Graph，避免了不稳定的关系建模。这种新的图构建范式随语料库规模线性扩展，且不产生额外的token消耗，为原始段落提供了经济且可靠的索引。在检索方面，LinearRAG采用两阶段策略：（i）通过局部语义桥接激活相关实体，然后（ii）通过全局重要性聚合进行段落检索。在四个数据集上的大量实验表明，LinearRAG显著优于基线模型。我们的代码和数据集可在 https://github.com/DEEP-PolyU/LinearRAG 获取。
英文摘要：
Retrieval-Augmented Generation (RAG) is widely used to mitigate hallucinations of Large Language Models (LLMs) by leveraging external knowledge. While effective for simple queries, traditional RAG systems struggle with large-scale, unstructured corpora where information is fragmented. Recent advances incorporate knowledge graphs to capture relational structures, enabling more comprehensive retrieval for complex, multi-hop reasoning tasks. However, existing graph-based RAG (GraphRAG) methods rely on unstable and costly relation extraction for graph construction, often producing noisy graphs with incorrect or inconsistent relations that degrade retrieval quality. In this paper, we revisit the pipeline of existing GraphRAG systems and propose LinearRAG (Linear Graph-based Retrieval-Augmented Generation), an efficient framework that enables reliable graph construction and precise passage retrieval. Specifically, LinearRAG constructs a relation-free hierarchical graph, termed Tri-Graph, using only lightweight entity extraction and semantic linking, avoiding unstable relation modeling. This new paradigm of graph construction scales linearly with corpus size and incurs no extra token consumption, providing an economical and reliable indexing of the original passages. For retrieval, LinearRAG adopts a two-stage strategy: (i) relevant entity activation via local semantic bridging, followed by (ii) passage retrieval through global importance aggregation. Extensive experiments on four datasets demonstrate that LinearRAG significantly outperforms baseline models. Our code and datasets are available at https://github.com/DEEP-PolyU/LinearRAG.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
