paper-with-me

Papers

LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora

2025-10-11 · Luyao Zhuang, Shengyuan Chen, Yilin Xiao, Huachi Zhou, Yujing Zhang, Hao Chen, Qinggang Zhang, Xiao Huang arxiv

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.

📄 PDF Abstract BibTeX arXiv:2510.10114

Code (0)

등록된 구현이 없습니다.

Tasks

Relation ExtractionPassage RetrievalKnowledge Graphs

Similar Papers 제목 키워드 기반

LiteRAG: Cost-Efficient Graph-Based Retrieval-Augmented Generation

2026-09-09 · Daniel Alejandro Coll Tejeda, Pedro García López, Daniel Barcelona-Pons arxiv

Graph-based retrieval can improve multi-hop question answering, but existing approaches often incur high query-time costs and produce diffuse, oversized contexts that reduce generation efficiency. We present LiteRAG, a g…

Multi-hop Question Answering

GRAG: Graph Retrieval-Augmented Generation

2024-05-26 · Yuntong Hu, Zhihan Lei, Zheng Zhang, Bo Pan 외

Naive Retrieval-Augmented Generation (RAG) focuses on individual documents during retrieval and, as a result, falls short in handling networked documents which are very popular in many applications such as citation graph…

Entity RetrievalKnowledge GraphsRAGRetrieval+1

CG-RAG: Research Question Answering by Citation Graph Retrieval-Augmented LLMs

2025-01-25 · Yuntong Hu, Zhihan Lei, Zhongjie Dai, Allen Zhang 외

Research question answering requires accurate retrieval and contextual understanding of scientific literature. However, current Retrieval-Augmented Generation (RAG) methods often struggle to balance complex document rela…

Information RetrievalQuestion AnsweringRAGRetrieval+1

GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation

2025-09-26 · Cehao Yang, Xiaojun Wu, Xueyuan Lin, Chengjin Xu 외 arxiv

Graph Retrieval-Augmented Generation (GraphRAG) enhances factual reasoning in LLMs by structurally modeling knowledge through graph-based representations. However, existing GraphRAG approaches face two core limitations: …

GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation

2025-02-03 · Linhao Luo, Zicheng Zhao, Gholamreza Haffari, Dinh Phung 외

Retrieval-augmented generation (RAG) has proven effective in integrating knowledge into large language models (LLMs). However, conventional RAGs struggle to capture complex relationships between pieces of knowledge, limi…

Graph Neural NetworkKnowledge GraphsRAGRetrieval+1