Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge Graphs

Dingjun Wu, Yukun Yan, Zhenghao Liu, Zhiyuan Liu, Maosong Sun

TL;DR

KG-Infused RAG introduces spreading activation over pre-existing large-scale knowledge graphs to augment corpus-based retrieval in RAG. By constructing a query-specific KG subgraph from seeds, expanding the query with KG-derived knowledge, and generating answers from multimodal evidence, the method achieves superior factual grounding and efficiency compared to ad-hoc KG approaches. The framework supports plug-in integration with existing RAG systems and is enhanced by Direct Preference Optimization to improve knowledge augmentation. Experiments on five QA benchmarks show consistent gains over vanilla RAG and competitive performance versus KG-based baselines, highlighting its practicality for open-domain QA with scalable, structured knowledge grounding.

Abstract

Retrieval-Augmented Generation (RAG) improves factual accuracy by grounding responses in external knowledge. However, existing RAG methods either rely solely on text corpora and neglect structural knowledge, or build ad-hoc knowledge graphs (KGs) at high cost and low reliability. To address these issues, we propose KG-Infused RAG, a framework that incorporates pre-existing large-scale KGs into RAG and applies spreading activation to enhance both retrieval and generation. KG-Infused RAG directly performs spreading activation over external KGs to retrieve relevant structured knowledge, which is then used to expand queries and integrated with corpus passages, enabling interpretable and semantically grounded multi-source retrieval. We further improve KG-Infused RAG through preference learning on sampled key stages of the pipeline. Experiments on five QA benchmarks show that KG-Infused RAG consistently outperforms vanilla RAG (by 3.9% to 17.8%). Compared with KG-based approaches such as GraphRAG and LightRAG, our method obtains structured knowledge at lower cost while achieving superior performance. Additionally, integrating KG-Infused RAG with Self-RAG and DeepNote yields further gains, demonstrating its effectiveness and versatility as a plug-and-play enhancement module for corpus-based RAG methods.

KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge Graphs

TL;DR

KG-Infused RAG introduces spreading activation over pre-existing large-scale knowledge graphs to augment corpus-based retrieval in RAG. By constructing a query-specific KG subgraph from seeds, expanding the query with KG-derived knowledge, and generating answers from multimodal evidence, the method achieves superior factual grounding and efficiency compared to ad-hoc KG approaches. The framework supports plug-in integration with existing RAG systems and is enhanced by Direct Preference Optimization to improve knowledge augmentation. Experiments on five QA benchmarks show consistent gains over vanilla RAG and competitive performance versus KG-based baselines, highlighting its practicality for open-domain QA with scalable, structured knowledge grounding.

Abstract

Retrieval-Augmented Generation (RAG) improves factual accuracy by grounding responses in external knowledge. However, existing RAG methods either rely solely on text corpora and neglect structural knowledge, or build ad-hoc knowledge graphs (KGs) at high cost and low reliability. To address these issues, we propose KG-Infused RAG, a framework that incorporates pre-existing large-scale KGs into RAG and applies spreading activation to enhance both retrieval and generation. KG-Infused RAG directly performs spreading activation over external KGs to retrieve relevant structured knowledge, which is then used to expand queries and integrated with corpus passages, enabling interpretable and semantically grounded multi-source retrieval. We further improve KG-Infused RAG through preference learning on sampled key stages of the pipeline. Experiments on five QA benchmarks show that KG-Infused RAG consistently outperforms vanilla RAG (by 3.9% to 17.8%). Compared with KG-based approaches such as GraphRAG and LightRAG, our method obtains structured knowledge at lower cost while achieving superior performance. Additionally, integrating KG-Infused RAG with Self-RAG and DeepNote yields further gains, demonstrating its effectiveness and versatility as a plug-and-play enhancement module for corpus-based RAG methods.

Paper Structure

This paper contains 70 sections, 12 equations, 2 figures, 26 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. Multi-Turn Retrieval in Retrieval-Augmented Generation
  4. Query Rewriting and Expansion.
  5. Evidence Aggregation and Enhancement.
  6. Knowledge Graphs Augmented Question Answering
  7. Methodology
  8. Task Definition
  9. Framework Overview
  10. KG-Guided Spreading Activation
  11. Seed Entities Initialization.
  12. Iterative Spreading Activation.
  13. Expanded Subgraph Summarization.
  14. KG-Augmented Answer Generation
  15. Passage Note Construction.
  16. ...and 55 more sections

Figures (2)

  • Figure 1: Overview of KG-Infused RAG. The framework consists of three modules: (1) KG-Guided Spreading Activation, (2) KG-Based Query Expansion, and (3) KG-Augmented Answer Generation, which together enable interpretable, fact-grounded multi-source retrieval.
  • Figure 2: Impact of the number of activation rounds on KG-Infused RAG. Vanilla RAG and Vanilla QE use Qwen2.5-7B-Instruct, while others use the DPO-trained version.