AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

LeanRAG: Knowledge-Graph-Based Generation with Semantic Aggregation and Hierarchical Retrieval

Yaoze Zhang, Rong Wu, Pinlong Cai, Xiaoman Wang, Guohang Yan, Song Mao, Ding Wang, Botian Shi

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 18 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 original text chunks to the generator context (ablation)LeanRAG · UltraDomain MixOverall score: 7.93 -> 8.59Improved
add original text chunks to the generator context (ablation)LeanRAG · UltraDomain CSOverall score: 8.34 -> 8.82Improved
add original text chunks to the generator context (ablation)LeanRAG · UltraDomain AgricultureOverall score: 8.53 -> 8.87Improved
add explicit inter-cluster aggregated relations (ablation)LeanRAG · UltraDomain CS, Diversity win ratewin rate: 66.0% vs 34.0%Improved
add explicit inter-cluster aggregated relations (ablation)LeanRAG · UltraDomain Mix, Comprehensiveness win ratewin rate: 51.5% vs 48.6%No clear effect
add explicit inter-cluster aggregated relations (ablation)LeanRAG · UltraDomain Mix, Overall win ratewin rate: 53.8% vs 46.2%Improved
LCA-based bottom-up hierarchical retrieval instead of community retrievalLeanRAG · Four UltraDomain datasets, Qwen3-14Bretrieved context tokens: 46% smaller on averageImproved
switch from HiRAG to LeanRAGKG-based RAG · UltraDomain MixOverall score: 8.08 -> 8.59Improved
switch from NaiveRAG/HiRAG to LeanRAGKG-based RAG · UltraDomain CS and AgricultureOverall score: CS 8.82 vs 8.77; Agriculture 8.87 vs 8.87No clear effect
switch from GraphRAG to LeanRAGKG-based RAG · UltraDomain Legal, ComprehensivenessComprehensiveness score: 8.95 -> 8.88Hurt

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