concept

GraphRAG-FI

Facts (11)

Sources

Empowering GraphRAG with Knowledge Filtering and Integration arxiv.org arXiv Mar 18, 2025 11 facts

claimThe authors claim that the GraphRAG-FI approach is effective across different retrieval paradigms and adaptable to various retrieval strategies in QA tasks.

measurementThe GraphRAG-FI method improves retrieval performance across two datasets, achieving an average improvement of 3.81% in Hit and 2.35% in F1 over the ROG retriever, 2.46% in Hit and 1.7% in F1 over the GNN-RAG retriever, and 7.47% in Hit and 4.88% in F1 over the SubgraphRAG retriever.

procedureThe GraphRAG-FI (Filtering & Integration) framework consists of two components: GraphRAG-Filtering, which uses a two-stage filtering mechanism to refine retrieved information, and GraphRAG-Integration, which uses a logits-based selection strategy to balance external knowledge with the large language model's intrinsic reasoning.

claimExperiments on knowledge graph question-answering tasks demonstrate that the GraphRAG-FI framework significantly improves reasoning performance across multiple backbone large language models.

referenceThe GraphRAG-FI framework consists of two core components: GraphRAG-Filtering, which removes irrelevant or misleading retrieved knowledge, and GraphRAG-Integration, which balances retrieved knowledge with the LLM's inherent reasoning ability to prevent the overuse of retrieved information.

measurementApplying the GraphRAG-FI method results in a 2.23% improvement in Hit and a 3.63% improvement in F1 over the ROG* baseline on the CWQ dataset when noise is present.

measurementThe GraphRAG-FI method yields an average increase of 5.03% in Hit and 3.70% in F1 compared to PageRank-based filtering across both the WebQSP and CWQ datasets.

measurementThe GraphRAG-FI method achieves an average improvement of 4.78% in Hit and 3.95% in F1 compared to similarity-based filtering when used with the ROG retriever across both the WebQSP and CWQ datasets.

procedureGraphRAG-FI utilizes a two-stage filtering mechanism called GraphRAG-Filtering to refine retrieved information and a logits-based selection strategy called GraphRAG-Integration to balance retrieval and intrinsic reasoning.

claimThe GraphRAG-FI (Filtering & Integration) framework improves reasoning accuracy in knowledge graph question answering tasks by mitigating noisy retrievals and excessive dependence on external knowledge.

measurementIn experiments on the WebQSP and CWQ datasets, the GNN-RAG + GraphRAG-FI method achieved the highest performance, with a Hit rate of 91.89% and F1 score of 75.98% on WebQSP, and a Hit rate of 71.12% and F1 score of 60.34% on CWQ.