Research map / Large language models / Retrieval and knowledge
Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving
Yao Cheng, Yibo Zhao, Jiapeng Zhu, Yao Liu, Xing Sun, Xiang Li
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 structured KG retrieval and mind-map reasoning over plain LLM | LLaMA2-13B · HotpotQA | Rouge-L: 19.1% -> 34.4% | Improved |
| use CogGRAG instead of Direct+KG | LLaMA2-13B · CWQ | Rouge-L: 39.7% -> 56.3% | Improved |
| CogGRAG vs RoG/GoG on WebQSP | LLaMA2-13B · WebQSP | EM: 62.8% -> 56.1% | Hurt |
| scale backbone from Qwen2.5-7B to Qwen2.5-32B | CogGRAG · HotpotQA | Rouge-L: 28.4% -> 40.5% | Improved |
| remove top-down problem decomposition (ablation) | CogGRAG · HotpotQA/CWQ/WebQSP | Rouge-L | Improved |
| add global-level retrieval (ablation) | CogGRAG · HotpotQA/CWQ/WebQSP | Rouge-L | Improved |
| add self-verification (ablation) | CogGRAG · HotpotQA/CWQ/WebQSP | Rouge-L | Improved |
| add selective abstention and verification | LLaMA2-13B · HotpotQA | hallucination rate: 50.5% (ToG) -> 25.0% | Improved |
| CogGRAG vs Graph-CoT on GRBench Healthcare | LLaMA2-13B · GRBench Healthcare | Rouge-L: 28.1% -> 27.4% | Hurt |
| CogGRAG vs Graph-CoT on GRBench Academic | LLaMA2-13B · GRBench Academic | Rouge-L: 19.3% -> 23.6% | Improved |
| CogGRAG vs Graph-CoT inference time | LLaMA2-13B · GRBench Academic | inference time (s): 22.39 -> 18.24 | Improved |
Closest papers by meaning
- Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation (ICLR 2025 · similarity 0.91)
- Simple is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation (ICLR 2025 · similarity 0.91)
- HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation (NeurIPS 2025 · similarity 0.88)
- StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization (ICLR 2025 · similarity 0.88)
- Debate on Graph: A Flexible and Reliable Reasoning Framework for Large Language Models (AAAI 2025 · similarity 0.88)
- Harnessing Large Language Models for Knowledge Graph Question Answering via Adaptive Multi-Aspect Retrieval-Augmentation (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.
