@inproceedings{yang-etal-2025-superrag,
    title = "{S}uper{RAG}: Beyond {RAG} with Layout-Aware Graph Modeling",
    author = "Yang, Chening  and
      Vu, Duy-Khanh  and
      Nguyen, Minh-Tien  and
      Nguyen, Xuan-Quang  and
      Nguyen, Linh  and
      Le, Hung",
    editor = "Chen, Weizhu  and
      Yang, Yi  and
      Kachuee, Mohammad  and
      Fu, Xue-Yong",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 3: Industry Track)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.naacl-industry.45/",
    pages = "544--557",
    ISBN = "979-8-89176-194-0",
    abstract = "This paper introduces layout-aware graph modeling for multimodal RAG. Different from traditional RAG methods that only deal with flat text chunks, the proposed method takes into account the relationship of multimodalities by using a graph structure. To do that, a graph modeling structure is defined based on document layout parsing. The structure of an input document is retained with the connection of text chunks, tables, and figures. This representation allows the method to handle complex questions that require information from multimodalities. To confirm the efficiency of the graph modeling, a flexible RAG pipeline is developed using robust components. Experimental results on four benchmark test sets confirm the contribution of the layout-aware modeling for performance improvement of the RAG pipeline."
}