@inproceedings{xu-etal-2025-equipping,
    title = "Equipping Retrieval-Augmented Large Language Models with Document Structure Awareness",
    author = "Xu, Lingnan  and
      Feng, Chong  and
      Zhang, Kaiyuan  and
      Zhengyong, Liu  and
      Xu, Wenqiang  and
      Meng, Fanqing",
    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/ingest-luhme/2025.findings-emnlp.1339/",
    doi = "10.18653/v1/2025.findings-emnlp.1339",
    pages = "24608--24631",
    ISBN = "979-8-89176-335-7",
    abstract = "While large language models (LLMs) demonstrate impressive capabilities, their reliance on parametric knowledge often leads to factual inaccuracies. Retrieval-Augmented Generation (RAG) mitigates this by leveraging external documents, yet existing approaches treat retrieved passages as isolated chunks, ignoring valuable structure that is crucial for document organization. Motivated by this gap, we propose \textit{ \textbf{R}etrieve-\textbf{D}ocument\textbf{R}oute-\textbf{R}ead} (\textbf{RDR2}), a novel framework that explicitly incorporates structural information throughout the RAG process. RDR2 employs an LLM-based router to dynamically navigate document structure trees, jointly evaluating content relevance and hierarchical relationships to assemble optimal evidence. Our key innovation lies in formulating document routing as a trainable task, with automatic action curation and structure-aware passage selection inspired by human reading strategies. Through comprehensive evaluation on five challenging datasets, RDR2 achieves state-of-the-art performance, demonstrating that explicit structural awareness significantly enhances RAG systems' ability to acquire and utilize knowledge, particularly in complex scenarios requiring multi-document synthesis."
}