Leveraging Spreading Activation for Improved Document Retrieval in Knowledge-Graph-Based RAG Systems

TL;DR

This paper introduces a novel RAG framework utilizing spreading activation on automatically constructed knowledge graphs, enhancing multi-hop reasoning and answer accuracy without relying on manual graph curation or large language model-guided traversal.

Contribution

The proposed method leverages spreading activation for document retrieval in RAG systems, reducing dependence on high-quality semantic graphs and improving multi-hop question answering performance.

Findings

Achieves up to 39% improvement in answer correctness with small models.

Performs better or comparable to state-of-the-art RAG methods.

Can be integrated as a plug-and-play module in various RAG pipelines.

Abstract

Despite initial successes and a variety of architectures, retrieval-augmented generation systems still struggle to reliably retrieve and connect the multi-step evidence required for complicated reasoning tasks. Most of the standard RAG frameworks regard all retrieved information as equally reliable, overlooking the varying credibility and interconnected nature of large textual corpora. GraphRAG approaches offer potential improvement to RAG systems by integrating knowledge graphs, which structure information into nodes and edges, capture entity relationships, and enable multi-step logical traversal. However, GraphRAG is not always an ideal solution, as it depends on high-quality graph representations of the corpus. Such representations usually rely on manually curated knowledge graphs, which are costly to construct and update, or on automated graph-construction pipelines that are often unreliable. Moreover, systems following this paradigm typically use large language models to guide graph traversal and evidence retrieval. In this paper, we propose a novel RAG framework that uses a spreading activation algorithm to retrieve information from a corpus of documents connected by an automatically constructed heterogeneous knowledge graph. This approach reduces reliance on semantic knowledge graphs, which are often incomplete due to information loss during information extraction, avoids LLM-guided graph traversal, and improves performance on multi-hop question answering. Experiments show that our method achieves better or comparable performance to several state-of-the-art RAG methods and can be integrated as a plug-and-play module with different iterative RAG pipelines. When combined with chain-of-thought iterative retrieval, it yields up to a 39% absolute improvement in answer correctness over naive RAG, while achieving these results with small open-weight language models.