@inproceedings{guo-etal-2025-empowering,
    title = "Empowering {G}raph{RAG} with Knowledge Filtering and Integration",
    author = "Guo, Kai  and
      Shomer, Harry  and
      Zeng, Shenglai  and
      Han, Haoyu  and
      Wang, Yu  and
      Tang, Jiliang",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.1293/",
    pages = "25450--25464",
    ISBN = "979-8-89176-332-6",
    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 {\&} 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."
}