mlsanityData to 14 Oct 2026

BambooKG: A Neurobiologically-inspired Frequency-Weight Knowledge Graph

arXiv 2510.25724 ↗First posted 29 Oct 2025cs.AIcited by 0

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

Abstract (arXiv)

Retrieval-Augmented Generation allows LLMs to access external knowledge, reducing hallucinations and ageing-data issues. However, it treats retrieved chunks independently and struggles with multi-hop or relational reasoning, especially across documents. Knowledge graphs enhance this by capturing the relationships between entities using triplets, enabling structured, multi-chunk reasoning. However, these tend to miss information that fails to conform to the triplet structure. We introduce BambooKG, a knowledge graph with frequency-based weights on non-triplet edges which reflect link strength, drawing on the Hebbian principle of "fire together, wire together". This decreases information loss and results in improved performance on single- and multi-hop reasoning, outperforming the existing solutions.

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 15 of its 25 references that are in the map. First posted on arXiv 29 Oct 2025.

Builds on

15 of 25 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes15 Apr
  2. 2025RAG vs. GraphRAG: A Systematic Evaluation and Key Insights17 Feb
  3. 2025Causal Graphs Meet Thoughts: Enhancing Complex Reasoning in Graph-Augmented LLMs24 Jan
  4. 2024Graph Retrieval-Augmented Generation: A Survey15 Aug
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr

Other references · 10

  1. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  2. 2024A Survey on LLM-as-a-Judgecited by 1,423
  3. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  4. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 257
  5. 2024The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinismcited by 116
  6. 2025Chain-of-Retrieval Augmented Generationcited by 49
  7. 2025KGGen: Extracting Knowledge Graphs from Plain Text with Language Modelscited by 49
  8. 2025Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learningcited by 39
  9. 2019Meta-Learning Deep Energy-Based Memory Modelscited by 11
  10. 2025The Dragon Hatchling: The Missing Link between the Transformer and Models of the Braincited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026LogosKG: Hardware-Optimized Scalable and Interpretable Knowledge Graph Retrieval
  2. 2025Think Parallax: Solving Multi-Hop Problems via Multi-View Knowledge-Graph-Based Retrieval-Augmented Generation
  3. 2025A Retrieval-Augmented Knowledge Mining Method with Deep Thinking LLMs for Biomedical Research and Clinical Support
  4. 2026Multi-hop Reasoning and Retrieval in Embedding Space: Leveraging Large Language Models with Knowledge
  5. 2025EcphoryRAG: Re-Imagining Knowledge-Graph RAG via Human Associative Memory
  6. 2025DrKGC: Dynamic Subgraph Retrieval-Augmented LLMs for Knowledge Graph Completion across General and Biomedical Domains
  7. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation
  8. 2026BubbleRAG: Evidence-Driven Retrieval-Augmented Generation for Black-Box Knowledge Graphs