mlsanityData to 14 Oct 2026

Path Pooling: Training-Free Structure Enhancement for Efficient Knowledge Graph Retrieval-Augmented Generation

arXiv 2503.05203 ↗First posted 7 Mar 2025cs.AI cs.CLcited by 0

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Although Large Language Models achieve strong success in many tasks, they still suffer from hallucinations and knowledge deficiencies in real-world applications. Many knowledge graph-based retrieval-augmented generation (KG-RAG) methods enhance the quality and credibility of LLMs by leveraging structure and semantic information in KGs as external knowledge bases. However, these methods struggle to effectively incorporate structure information, either incurring high computational costs or underutilizing available knowledge. Inspired by smoothing operations in graph representation learning, we propose path pooling, a simple, training-free strategy that introduces structure information through a novel path-centric pooling operation. It seamlessly integrates into existing KG-RAG methods in a plug-and-play manner, enabling richer structure information utilization. Extensive experiments demonstrate that incorporating the path pooling into the state-of-the-art KG-RAG method consistently improves performance across various settings while introducing negligible additional cost.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 30 of its 44 references that are in the map. First posted on arXiv 7 Mar 2025.

Builds on

30 of 44 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Graph Retrieval-Augmented Generation: A Survey15 Aug
  2. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoning30 May
  3. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr

Other references · 27

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2018Hierarchical Graph Representation Learning with Differentiable Poolingcited by 787
  6. 2023Unifying Large Language Models and Knowledge Graphs: A Roadmapcited by 668
  7. 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
  8. 2017Representation Learning on Graphs: Methods and Applicationscited by 457
  9. 2018The Web as a Knowledge-base for Answering Complex Questionscited by 410
  10. 2021Beyond Low-frequency Information in Graph Convolutional Networkscited by 362
  11. 2023StructGPT: A General Framework for Large Language Model to Reason over Structured Datacited by 343
  12. 2023Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoningcited by 328
15 more
  1. 2023Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graphcited by 238
  2. 2024mGTE: Generalized Long-Context Text Representation and Reranking Models for Multilingual Text Retrievalcited by 236
  3. 2024RankRAG: Unifying Context Ranking with Retrieval-Augmented Generation in LLMscited by 202
  4. 2023OpenAGI: When LLM Meets Domain Expertscited by 197
  5. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 123
  6. 2023Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answeringcited by 119
  7. 2024Found in the Middle: Calibrating Positional Attention Bias Improves Long Context Utilizationcited by 101
  8. 2023Knowledge-Driven CoT: Exploring Faithful Reasoning in LLMs for Knowledge-intensive Question Answeringcited by 97
  9. 2023Attention Sorting Combats Recency Bias In Long Context Language Modelscited by 90
  10. 2022The NLP Task Effectiveness of Long-Range Transformerscited by 22
  11. 2024GraphInsight: Unlocking Insights in Large Language Models for Graph Structure Understandingcited by 18
  12. 2024FunnelRAG: A Coarse-to-Fine Progressive Retrieval Paradigm for RAGcited by 18
  13. 2023Faithful Question Answering with Monte-Carlo Planningcited by 16
  14. 2024Position Engineering: Boosting Large Language Models through Positional Information Manipulationcited by 9
  15. 2024Attention Instruction: Amplifying Attention in the Middle via Promptingcited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Query-Aware Multi-Path Knowledge Graph Fusion Approach for Enhancing Retrieval-Augmented Generation in Large Language Models
  2. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
  3. 2025Walk&Retrieve: Simple Yet Effective Zero-shot Retrieval-Augmented Generation via Knowledge Graph Walks
  4. 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Models
  5. 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
  6. 2026BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs
  7. 2025Weak-to-Strong GraphRAG: Aligning Weak Retrievers with Large Language Models for Graph-based Retrieval Augmented Generation
  8. 2025Less is More: Denoising Knowledge Graphs For Retrieval Augmented Generation