让大模型读文档时理解结构，提升事实准确性。
Equipping Retrieval-Augmented Large Language Models with Document Structure Awareness
- 用可训练的路由机制动态导航文档层级结构
- 在5个数据集上达到当前最优，多文档推理效果显著提升
- 适合需要精准跨文档归纳的复杂问答场景
尽管大语言模型表现出强大能力，但其依赖参数化知识常导致事实错误。检索增强生成（RAG）通过利用外部文档缓解此问题，但现有方法将检索片段视为孤立块，忽略对文档组织至关重要的结构信息。为此，我们提出RDR2框架，显式在RAG全流程中融入结构信息。RDR2采用基于大模型的路由器，动态遍历文档结构树，联合评估内容相关性与层级关系，以组装最优证据。其核心创新在于将文档路由建模为可训练任务，通过自动动作筛选与结构感知的段落选择，借鉴人类阅读策略。在五个挑战性数据集上的全面评估表明，RDR2达到当前最优性能，证明显式结构意识能显著提升RAG系统在复杂场景下获取和利用知识的能力，尤其在需要多文档综合的任务中表现突出。
原文摘要 · Abstract (English)
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 Retrieve-DocumentRoute-Read (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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。