TOBUGraph: Knowledge Graph-Based Retrieval for Enhanced LLM Performance Beyond RAG
Savini Kashmira, Jayanaka L. Dantanarayana, Joshua Brodsky, Ashish Mahendra, Yiping Kang, Krisztian Flautner, Lingjia Tang, Jason Mars

TL;DR
TOBUGraph introduces a graph-based retrieval method that constructs dynamic knowledge graphs from unstructured data, improving retrieval accuracy and reducing hallucinations in large language models compared to traditional RAG techniques.
Contribution
The paper presents a novel graph-based retrieval framework that automatically constructs knowledge graphs from unstructured data, surpassing RAG's limitations in semantic understanding and hallucination reduction.
Findings
TOBUGraph outperforms RAG in precision and recall.
It reduces hallucinations in LLM retrieval.
Effective in real-world personal memory applications.
Abstract
Retrieval-Augmented Generation (RAG) is one of the leading and most widely used techniques for enhancing LLM retrieval capabilities, but it still faces significant limitations in commercial use cases. RAG primarily relies on the query-chunk text-to-text similarity in the embedding space for retrieval and can fail to capture deeper semantic relationships across chunks, is highly sensitive to chunking strategies, and is prone to hallucinations. To address these challenges, we propose TOBUGraph, a graph-based retrieval framework that first constructs the knowledge graph from unstructured data dynamically and automatically. Using LLMs, TOBUGraph extracts structured knowledge and diverse relationships among data, going beyond RAG's text-to-text similarity. Retrieval is achieved through graph traversal, leveraging the extracted relationships and structures to enhance retrieval accuracy,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
Taxonomy
TopicsTopic Modeling · Context-Aware Activity Recognition Systems · Advanced Graph Neural Networks
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · Attention Is All You Need · Linear Layer · Dense Connections · Byte Pair Encoding · Residual Connection · Multi-Head Attention · Weight Decay · WordPiece · Softmax
