AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

Topology of Reasoning: Retrieved Cell Complex-Augmented Generation for Textual Graph Question Answering

Sen Zhao, Lincheng Zhou, Yue Chen, Ding Zou

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Knowledge graph reasoning with LLMs · 0 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 Cellular Representation Lifting (2-cells for cycles) (ablation)TopoRAG w/ LoRA · ExplaGraphsaccuracy: 0.8576 -> 0.9151Improved
add Cellular Representation Lifting (ablation)TopoRAG w/ LoRA · WebQSPHit: 84.96 -> 90.66Improved
add Topology-aware Subcomplex Retrieval instead of shortest path (ablation)TopoRAG w/ LoRA · ExplaGraphsaccuracy: 0.8524 -> 0.9151Improved
add Topology-aware Subcomplex Retrieval (ablation)TopoRAG w/ LoRA · WebQSPHit: 84.23 -> 90.66Improved
add Multi-dimensional Topological Reasoning instead of GCN (ablation)TopoRAG w/ LoRA · ExplaGraphsaccuracy: 0.8611 -> 0.9151Improved
add Multi-dimensional Topological Reasoning (ablation)TopoRAG w/ LoRA · WebQSPHit: 85.46 -> 90.66Improved
use BFS instead of DFS spanning tree (ablation)TopoRAG w/ LoRA · WebQSPHit: 90.66 -> 90.18No clear effect
use random instead of DFS spanning tree (ablation)TopoRAG w/ LoRA · ExplaGraphsaccuracy: 0.9151 -> 0.9187No clear effect
add LoRA tuning of the LLM to TopoRAGTopoRAG · WebQSPHit: 87.10 -> 90.66Improved
add LoRA tuning of the LLM to TopoRAGTopoRAG · ExplaGraphsaccuracy: 0.8899 -> 0.9151Improved
replace G-Retriever with TopoRAG (frozen LLM)G-Retriever · SceneGraphsaccuracy: 0.8131 -> 0.8362Improved
increase top-k of 2-cells from 1 to 3 (ablation)TopoRAG · WebQSPnumber of 2-cells retrieved: 2 -> 4Mixed

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