UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough

TL;DR

UnWeaver introduces a simplified RAG framework that uses entity-based decomposition to improve retrieval fidelity and reduce noise, addressing limitations of traditional vector and graph-based RAG systems.

Contribution

It proposes UnWeaver, a novel framework that leverages entity decomposition with LLMs to enhance retrieval accuracy and reduce complexity in RAG systems.

Findings

Entity-based decomposition improves retrieval fidelity.

Reduces noise in indexing and generation.

Simplifies the complexity compared to graph-based RAG.

Abstract

One of the key problems in Retrieval-augmented generation (RAG) systems is that chunk-based retrieval pipelines represent the source chunks as atomic objects, mixing the information contained within such a chunk into a single vector. These vector representations are then fundamentally treated as isolated, independent and self-sufficient, with no attempt to represent possible relations between them. Such an approach has no dedicated mechanisms for handling multi-hop questions. Graph-based RAG systems aimed to ameliorate this problem by modeling information as knowledge-graphs, with entities represented by nodes being connected by robust relations, and forming hierarchical communities. This approach however suffers from its own issues with some of them being: orders of magnitude increased componential complexity in order to create graph-based indices, and reliance on heuristics for performing retrieval. We propose UnWeaver, a novel RAG framework simplifying the idea of GraphRAG. UnWeaver disentangles the contents of the documents into entities which can occur across multiple chunks using an LLM. In the retrieval process entities are used as an intermediate way of recovering original text chunks hence preserving fidelity to the source material. We argue that entity-based decomposition yields a more distilled representation of original information, and additionally serves to reduce noise in the indexing, and generation process.