@inproceedings{kim-etal-2025-regraphrag,
    title = "{R}e{G}raph{RAG}: Reorganizing Fragmented Knowledge Graphs for Multi-Perspective Retrieval-Augmented Generation",
    author = "Kim, Soohyeong  and
      Hwang, Seok Jun  and
      Kim, JungHyoun  and
      Park, Jeonghyeon  and
      Choi, Yong Suk",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.290/",
    doi = "10.18653/v1/2025.findings-emnlp.290",
    pages = "5426--5443",
    ISBN = "979-8-89176-335-7",
    abstract = "Recent advancements in Retrieval-Augmented Generation (RAG) have improved large language models (LLMs) by incorporating external knowledge at inference time. Graph-based RAG systems have emerged as promising approaches, enabling multi-hop reasoning by organizing retrieved information into structured graphs. However, when knowledge graphs are constructed from unstructured documents using LLMs, they often suffer from fragmentation{---}resulting in disconnected subgraphs that limit inferential coherence and undermine the advantages of graph-based retrieval. To address these limitations, we propose ReGraphRAG, a novel framework designed to reconstruct and enrich fragmented knowledge graphs through three core components: Graph Reorganization, Perspective Expansion, and Query-aware Reranking. Experiments on four benchmarks show that ReGraphRAG outperforms state-of-the-art baselines, achieving over 80{\%} average diversity win rate. Ablation studies highlight the key contributions of graph reorganization and especially perspective expansion to performance gains. Our code is available at: https://anonymous.4open.science/r/ReGraphRAG-7B73"
}