Empowering GraphRAG with Knowledge Filtering and Integration
Preprint
Abstract
In recent years, large language models (LLMs) have revolutionized the field of natural language processing. However, they often suffer from knowledge gaps and hallucinations. Graph retrieval-augmented generation (GraphRAG) enhances LLM reasoning by integrating structured knowledge from external graphs. However, we identify two key challenges that plague GraphRAG:(1) Retrieving noisy and irrelevant information can degrade performance and (2)Excessive reliance on external knowledge suppresses the model's intrinsic reasoning. To address these issues, we propose GraphRAG-FI (Filtering and Integration), consisting of GraphRAG-Filtering and GraphRAG-Integration. GraphRAG-Filtering employs a two-stage filtering mechanism to refine retrieved information. GraphRAG-Integration employs a logits-based selection strategy to balance external knowledge from GraphRAG with the LLM's intrinsic reasoning,reducing over-reliance on retrievals. Experiments on knowledge graph QA tasks demonstrate that GraphRAG-FI significantly improves reasoning performance across multiple backbone models, establishing a more reliable and effective GraphRAG framework.Keywords
All Related Versions
This publication has 10 references indexed in Scilit:
- A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open QuestionsACM Transactions on Information Systems, 2025
- FRAG: A Flexible Modular Framework for Retrieval-Augmented Generation based on Knowledge Graphs2025
- Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective2025
- Reasoning on Efficient Knowledge Paths: Knowledge Graph Guides Large Language Model for Domain Question Answering2024
- G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering2024
- When Do LLMs Need Retrieval Augmentation? Mitigating LLMs’ Overconfidence Helps Retrieval Augmentation2024
- The Good and The Bad: Exploring Privacy Issues in Retrieval-Augmented Generation (RAG)2024
- Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning2023
- Self-Knowledge Guided Retrieval Augmentation for Large Language Models2023
- The Web as a Knowledge-Base for Answering Complex Questions2018