AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

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

Luyao Zhuang, Shengyuan Chen, Yilin Xiao, Huachi Zhou, Yujing Zhang, Hao Chen, Qinggang Zhang, Xiao Huang

ICLR 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 67 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add relevant entity activation via semantic bridging (ablation)LinearRAG · four datasetsaverage of GPT-Acc and Contain-AccImproved
add global importance aggregation via personalized PageRank (ablation)LinearRAG · four datasetsaverage of GPT-Acc and Contain-AccImproved
replace all-mpnet-base-v2 with e5-large-v2LinearRAG · HotpotQAContain-Acc: 64.30 -> 66.80Improved
replace all-mpnet-base-v2 with e5-large-v2LinearRAG · MuSiQueContain-Acc: 33.90 -> 31.70Hurt
replace all-mpnet-base-v2 with all-MiniLM-L6-v2LinearRAG · MedicalGPT-Acc: 63.72 -> 62.32Hurt
replace all-mpnet-base-v2 with bge-large-en-v1.5LinearRAG · MedicalGPT-Acc: 63.72 -> 64.45Improved
use LinearRAG instead of HippoRAG2 graph constructionHippoRAG2 · 2WikiGPT-Acc: 55.00 -> 63.70Improved
add graph retrieval (GFM-RAG) over vanilla RAGVanilla RAG top-5 · creative generation (Medical)relevance: 58.73 -> 22.87Hurt
add graph retrieval (GFM-RAG) over vanilla RAGVanilla RAG top-5 · creative generation (Medical)evidence recall: 44.88 -> 83.51Improved
use LinearRAG instead of GFM-RAGGFM-RAG · complex reasoning (Medical)relevance: 33.06 -> 81.58Improved
use LinearRAG instead of RAPTOR indexingRAPTOR · ATLAS-Wiki 10M tokensindexing time (s): 46430.96 -> 3084.38Improved
increase retrieved passages from top-1 to top-5vanilla RAG · MuSiQueGPT-Acc: 21.10 -> 29.60Improved

Later papers that compared with this method

2 later accepted papers report LinearRAG as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy