TL;DR
PathRAG introduces a graph-based retrieval method that prunes redundant information and uses relational paths to enhance the coherence and quality of responses generated by large language models.
Contribution
It presents a novel approach that retrieves and utilizes relational paths from an indexing graph, improving over flat retrieval structures in RAG systems.
Findings
Outperforms state-of-the-art baselines across six datasets
Reduces redundant information through flow-based pruning
Enhances response coherence with path-based prompting
Abstract
Retrieval-augmented generation (RAG) improves the response quality of large language models (LLMs) by retrieving knowledge from external databases. Typical RAG approaches split the text database into chunks, organizing them in a flat structure for efficient searches. To better capture the inherent dependencies and structured relationships across the text database, researchers propose to organize textual information into an indexing graph, known asgraph-based RAG. However, we argue that the limitation of current graph-based RAG methods lies in the redundancy of the retrieved information, rather than its insufficiency. Moreover, previous methods use a flat structure to organize retrieved information within the prompts, leading to suboptimal performance. To overcome these limitations, we propose PathRAG, which retrieves key relational paths from the indexing graph, and converts these paths…
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.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsRefunds@Expedia|||How do I get a full refund from Expedia? · Attention Is All You Need · Byte Pair Encoding · Dense Connections · Attention Dropout · Residual Connection · Linear Layer · Layer Normalization · Linear Warmup With Linear Decay · Weight Decay
