{"ID":2848691,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.25724","arxiv_id":"2510.25724","title":"BambooKG: A Neurobiologically-inspired Frequency-Weight Knowledge Graph","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.","short_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 betwe...","url_abs":"https://arxiv.org/abs/2510.25724","url_pdf":"https://arxiv.org/pdf/2510.25724v1","authors":"[\"Vanya Arikutharam\",\"Arkadiy Ukolov\"]","published":"2025-10-29T17:31:27Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"RAG\",\"Large Language Model\"]","has_code":false}