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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add Cellular Representation Lifting (2-cells for cycles) (ablation) | TopoRAG w/ LoRA · ExplaGraphs | accuracy: 0.8576 -> 0.9151 | Improved |
| add Cellular Representation Lifting (ablation) | TopoRAG w/ LoRA · WebQSP | Hit: 84.96 -> 90.66 | Improved |
| add Topology-aware Subcomplex Retrieval instead of shortest path (ablation) | TopoRAG w/ LoRA · ExplaGraphs | accuracy: 0.8524 -> 0.9151 | Improved |
| add Topology-aware Subcomplex Retrieval (ablation) | TopoRAG w/ LoRA · WebQSP | Hit: 84.23 -> 90.66 | Improved |
| add Multi-dimensional Topological Reasoning instead of GCN (ablation) | TopoRAG w/ LoRA · ExplaGraphs | accuracy: 0.8611 -> 0.9151 | Improved |
| add Multi-dimensional Topological Reasoning (ablation) | TopoRAG w/ LoRA · WebQSP | Hit: 85.46 -> 90.66 | Improved |
| use BFS instead of DFS spanning tree (ablation) | TopoRAG w/ LoRA · WebQSP | Hit: 90.66 -> 90.18 | No clear effect |
| use random instead of DFS spanning tree (ablation) | TopoRAG w/ LoRA · ExplaGraphs | accuracy: 0.9151 -> 0.9187 | No clear effect |
| add LoRA tuning of the LLM to TopoRAG | TopoRAG · WebQSP | Hit: 87.10 -> 90.66 | Improved |
| add LoRA tuning of the LLM to TopoRAG | TopoRAG · ExplaGraphs | accuracy: 0.8899 -> 0.9151 | Improved |
| replace G-Retriever with TopoRAG (frozen LLM) | G-Retriever · SceneGraphs | accuracy: 0.8131 -> 0.8362 | Improved |
| increase top-k of 2-cells from 1 to 3 (ablation) | TopoRAG · WebQSP | number of 2-cells retrieved: 2 -> 4 | Mixed |
Closest papers by meaning
- Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation (ICLR 2025 · similarity 0.91)
- Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation (ICLR 2025 · similarity 0.91)
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering (NeurIPS 2024 · similarity 0.90)
- Talk like a Graph: Encoding Graphs for Large Language Models (ICLR 2024 · similarity 0.88)
- HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation (NeurIPS 2025 · similarity 0.88)
- Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models (AAAI 2025 · similarity 0.88)
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.
