Improving LLM Retrieval with GraphRAG-SF: Semantic Filtering for Graph-Based RAG Systems
Published in IEEE International Conference on Big Data (IEEE Big Data 2025), 2025
Graph-based Retrieval-Augmented Generation (RAG) systems enhance LLM responses by structuring knowledge as graphs. This paper introduces GraphRAG-SF, a semantic filtering approach that improves retrieval precision in graph-based RAG by filtering irrelevant subgraph traversals before they reach the LLM context window. Our method reduces noise in retrieved context while maintaining recall, leading to more accurate and grounded LLM responses.
Recommended citation: @inproceedings{hosseini2025graphragsf, title={Improving LLM Retrieval with GraphRAG-SF: Semantic Filtering for Graph-Based RAG Systems}, author={Hosseini, Mohammad-Parsa and Shah, Ankit and Miao, Connie and Wei, Wei}, booktitle={2025 IEEE International Conference on Big Data (Big Data)}, pages={2561--2568}, year={2025}, organization={IEEE} }
Download Paper