DocSage：一个多文档多实体问答的信息结构代理
DocSage: An Information Structuring Agent for Multi-Doc Multi-Entity Question Answering
AI总结：
DocSage通过动态模式发现、结构化信息提取和模式感知推理，解决多文档多实体问答中的跨文档证据链构建和实体关系推断问题，实现超过27%的准确率提升。
摘要：
多文档多实体问答本质上要求模型跟踪多个实体在分散文档中的隐含逻辑。然而，现有的大型语言模型（LLMs）和检索增强生成（RAG）框架存在关键限制：标准RAG的向量相似性基于粗粒度检索往往遗漏关键事实，基于图的RAG无法有效整合碎片化的复杂关系网络，且两者均缺乏模式意识，导致跨文档证据链构建不足和实体关系推断不准确。为解决这些挑战，我们提出了DocSage，一种端到端的代理框架，集成了动态模式发现、结构化信息提取和模式感知的关系推理，并具有误差保证。DocSage通过三个核心模块运作：（1）一个模式发现模块动态推断查询特定的最小可连接模式以捕捉关键实体和关系；（2）一个提取模块将无结构文本转换为语义连贯的关系表，通过带有误差意识的纠正机制来减少提取错误；（3）一个推理模块在结构化表上执行多跳关系推理，利用模式意识高效对齐跨文档实体并汇总证据。这种代理设计提供了三个关键优势：通过SQL驱动的索引实现精确事实定位，通过关系表自然支持跨文档实体连接，以及通过结构化表示缓解LLM注意力扩散。在两个MDMEQA基准测试中，DocSage显著优于最先进的长上下文LLM和RAG系统，分别实现了超过27%的准确率提升。
英文摘要：
Multi-document Multi-entity Question Answering inherently demands models to track implicit logic between multiple entities across scattered documents. However, existing Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) frameworks suffer from critical limitations: standard RAG's vector similarity-based coarse-grained retrieval often omits critical facts, graph-based RAG fails to efficiently integrate fragmented complex relationship networks, and both lack schema awareness, leading to inadequate cross-document evidence chain construction and inaccurate entity relationship deduction. To address these challenges, we propose DocSage, an end-to-end agentic framework that integrates dynamic schema discovery, structured information extraction, and schema-aware relational reasoning with error guarantees. DocSage operates through three core modules: (1) A schema discovery module dynamically infers query-specific minimal joinable schemas to capture essential entities and relationships; (2) An extraction module transforms unstructured text into semantically coherent relational tables, enhanced by error-aware correction mechanisms to reduce extraction errors; (3) A reasoning module performs multi-hop relational reasoning over structured tables, leveraging schema awareness to efficiently align cross-document entities and aggregate evidence. This agentic design offers three key advantages: precise fact localization via SQL-powered indexing, natural support for cross-document entity joins through relational tables, and mitigated LLM attention diffusion via structured representation. Evaluations on two MDMEQA benchmarks demonstrate that DocSage significantly outperforms state-of-the-art long-context LLMs and RAG systems, achieving more than 27% accuracy improvements respectively.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
