Saved in:
Bibliographic Details
Main Authors: Arikutharam, Vanya, Ukolov, Arkadiy
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2510.25724
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908619213111296
author Arikutharam, Vanya
Ukolov, Arkadiy
author_facet Arikutharam, Vanya
Ukolov, Arkadiy
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2510_25724
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BambooKG: A Neurobiologically-inspired Frequency-Weight Knowledge Graph
Arikutharam, Vanya
Ukolov, Arkadiy
Artificial Intelligence
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.
title BambooKG: A Neurobiologically-inspired Frequency-Weight Knowledge Graph
topic Artificial Intelligence
url https://arxiv.org/abs/2510.25724