Redirecting to original paper in 30 seconds...
Click below to go immediately or wait for automatic redirect
📄 Abstract
Abstract: 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.
Authors (2)
Vanya Arikutharam
Arkadiy Ukolov
Submitted
October 29, 2025
Key Contributions
Introduces BambooKG, a neurobiologically-inspired knowledge graph with frequency-based weights on non-triplet edges, reflecting link strength based on the Hebbian principle. This reduces information loss and improves performance on single- and multi-hop reasoning.
Business Value
Enhances the reasoning capabilities of LLMs, leading to more accurate and insightful answers for complex queries, particularly in knowledge-intensive domains.