AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

T-Retriever: Tree-based Hierarchical Retrieval Augmented Generation for Textual Graphs

Chunyu Wei, Huaiyu Qin, Siyuan He, Yunhai Wang, Yueguo Chen

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation · 1 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
jointly optimize structure and semantics (S2-Entropy) instead of semantic-only (ablation)T-Retriever · WebQSPaccuracy: 0.6319 -> 0.7715Improved
jointly optimize structure and semantics (S2-Entropy) instead of structural-only (ablation)T-Retriever · WebQSPaccuracy: 0.7154 -> 0.7715Improved
structural entropy contributes more than semantic entropy alone (ablation)T-Retriever · WebQSPaccuracy: 0.6319 (semantic) vs 0.7154 (structural)Mixed
use T-Retriever instead of ArchRAGT-Retriever · BookGraphsaccuracy: 0.7108 -> 0.7579Improved
use T-Retriever instead of ArchRAGT-Retriever · SceneGraphsaccuracy: 0.8212 -> 0.8507Improved
use T-Retriever instead of fine-tuned G-Retriever w/ LoRAT-Retriever · WebQSPaccuracy: 0.7186 -> 0.7715Improved
use semantics-first RAPTOR hierarchy ignoring topologyRAPTOR · WebQSPaccuracy: 0.7254 -> 0.7114 (vs GRAG w/ LoRA)Hurt
add hierarchy (structure-first ArchRAG) over flat methodsArchRAG · WebQSPaccuracy: 0.7254 -> 0.7533Improved
increase encoding tree depth L (ablation)T-Retriever · SceneGraphs, WebQSP, BookGraphsaccuracyImproved
retrieve more subgraphs (k beyond about 6) on larger graphs (ablation)T-Retriever · larger graphsaccuracyMixed
set lambda around 1.0 to 1.5 (ablation)T-Retriever · WebQSPaccuracyImproved
replace G-Retriever retrieval with encoding-tree retrievalT-Retriever · WebQSPavg tokens: 721.0 -> 114.2Improved

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