StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization

TL;DR

StructRAG is a novel framework that enhances LLMs' reasoning by converting scattered knowledge into structured formats, significantly improving performance on complex knowledge-intensive tasks.

Contribution

It introduces a method to identify optimal knowledge structures and reconstruct documents accordingly, advancing retrieval-augmented generation techniques.

Findings

Achieves state-of-the-art results on various tasks.

Excels in challenging knowledge-intensive scenarios.

Demonstrates effective knowledge structuring improves reasoning.

Abstract

Retrieval-augmented generation (RAG) is a key means to effectively enhance large language models (LLMs) in many knowledge-based tasks. However, existing RAG methods struggle with knowledge-intensive reasoning tasks, because useful information required to these tasks are badly scattered. This characteristic makes it difficult for existing RAG methods to accurately identify key information and perform global reasoning with such noisy augmentation. In this paper, motivated by the cognitive theories that humans convert raw information into various structured knowledge when tackling knowledge-intensive reasoning, we proposes a new framework, StructRAG, which can identify the optimal structure type for the task at hand, reconstruct original documents into this structured format, and infer answers based on the resulting structure. Extensive experiments across various knowledge-intensive tasks show that StructRAG achieves state-of-the-art performance, particularly excelling in challenging scenarios, demonstrating its potential as an effective solution for enhancing LLMs in complex real-world applications.