Research map / Large language models / Retrieval and knowledge
Cog-RAG: Cognitive-Inspired Dual-Hypergraph with Theme Alignment Retrieval-Augmented Generation
Hao Hu, Yifan Feng, Ruoxue Li, Rundong Xue, Xingliang Hou, Zhiqiang Tian, Yue Gao, Shaoyi Du
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 entity hypergraph (ablation) | Cog-RAG · Mix | overall score: 76.58 -> 85.39 | Improved |
| add entity hypergraph (ablation) | Cog-RAG · CS | overall score: 84.58 -> 87.07 | Improved |
| add theme hypergraph (ablation) | Cog-RAG · CS | overall score: 85.88 -> 87.07 | Improved |
| add theme hypergraph (ablation) | Cog-RAG · Neurology | overall score: 85.41 -> 86.55 | Improved |
| add theme hypergraph (ablation) | Cog-RAG · Mix | overall score: 84.82 -> 85.39 | No clear effect |
| add two-stage retrieval instead of concatenating both hypergraph results (ablation) | Cog-RAG · Mix | overall score: 84.88 -> 85.39 | Improved |
| add two-stage retrieval instead of concatenating both hypergraph results (ablation) | Cog-RAG · Neurology | overall score: 86.18 -> 86.55 | Improved |
| use Cog-RAG instead of NaiveRAG | Cog-RAG · Agriculture | overall win rate: 2.8% vs 97.2% | Improved |
| use Cog-RAG instead of Hyper-RAG | Cog-RAG · Pathology | overall win rate: 36.8% vs 63.2% | Improved |
| use Cog-RAG instead of Hyper-RAG | Cog-RAG · Mix | overall win rate: 46.8% vs 53.2% | Improved |
Closest papers by meaning
- HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation (NeurIPS 2025 · similarity 0.89)
- A Systematic Exploration of Knowledge Graph Alignment with Large Language Models in Retrieval Augmented Generation (AAAI 2025 · similarity 0.89)
- GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation (NeurIPS 2025 · similarity 0.88)
- Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation (ICLR 2025 · similarity 0.88)
- Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting (ICLR 2025 · similarity 0.87)
- CogniVerse: Revolutionizing Multi-Modal Retrieval-Augmented Generation with Cognitive Reflection and Geometric Reasoning (CVPR 2026 · similarity 0.87)
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.
