@inproceedings{bu-etal-2025-query,
    title = "Query-Driven Multimodal {G}raph{RAG}: Dynamic Local Knowledge Graph Construction for Online Reasoning",
    author = "Bu, Chenyang  and
      Chang, Guojie  and
      Chen, Zihao  and
      Dang, CunYuan  and
      Wu, Zhize  and
      He, Yi  and
      Wu, Xindong",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/mtsummit-25-ingestion/2025.findings-acl.1100/",
    doi = "10.18653/v1/2025.findings-acl.1100",
    pages = "21360--21380",
    ISBN = "979-8-89176-256-5",
    abstract = "An increasing adoption of Large Language Models (LLMs) in complex reasoning tasks necessitates their interpretability and reliability. Recent advances to that end include retrieval-augmented generation (RAG) and knowledge graph-enhanced RAG (GraphRAG), whereas they are constrained by static knowledge bases and ineffective multimodal data integration. In response, we propose a Query-Driven Multimodal GraphRAG framework that dynamically constructs local knowledge graphs tailored to query semantics. Our approach 1) derives graph patterns from query semantics to guide knowledge extraction, 2) employs a multi-path retrieval strategy to pinpoint core knowledge, and 3) supplements missing multimodal information ad hoc. Experimental results on the MultimodalQA and WebQA datasets demonstrate that our framework achieves the state-of-the-art performance among unsupervised competitors, particularly excelling in cross-modal understanding of complex queries."
}