BambooKG: A Neurobiologically-inspired Frequency-Weight Knowledge Graph
This addresses the issue of multi-hop and relational reasoning across documents for users of retrieval-augmented generation systems, though it appears incremental as it builds on existing knowledge graph methods.
The paper tackled the problem of information loss in knowledge graphs for retrieval-augmented generation by introducing BambooKG, a neurobiologically-inspired graph with frequency-weighted edges, which improved performance on single- and multi-hop reasoning tasks compared to existing solutions.
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.