arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2504.09554cs.IR
收藏

混合RAG:利用大语言模型整合文本和表格

Mixture-of-RAG: Integrating Text and Tables with Large Language Models

Beijing Institute of Technology(北京理工大学);Zhejiang Gongshang University(浙江工商大学)

Chi Zhang, Qiyang Chen, Mengqi Zhang

AI总结:

MixRAG通过三阶段框架整合文本和表格,提升异构文档检索性能,实现混合模态文档接地的最新成果。

摘要:

大型语言模型(LLMs)在响应基于外部知识源时能够实现最优效用。然而,现实中的文档,如年度报告、科学论文和临床指南,经常结合大量的叙述内容与复杂的、层次结构化的表格。尽管现有的检索增强生成(RAG)系统能够有效整合LLMs的生成能力与外部检索信息,但其性能在处理这种异构的文本-表格层次结构时显著下降。为了解决这一限制,我们正式提出了异构文档RAG任务,该任务需要在文本和层次化表格数据之间进行联合检索和推理。我们提出了MixRAG,一种新的三阶段框架:(i)层次行-列级(H-RCL)表示,该表示保留层次结构和异构关系;(ii)一个基于LLM的检索器进行证据对齐;(iii)通过RECAP提示策略进行多步骤推理分解。为弥补该领域可用数据的差距,我们发布了DocRAGLib数据集,一个包含2000份文档的语料库,配以自动对齐的文本-表格摘要和黄金文档注释。全面的实验结果表明,MixRAG在文本-only、表格-only和朴素混合基线上将top-1检索提升46%,在混合模态文档接地任务中建立了新的最先进的性能。

英文摘要:

Large language models (LLMs) achieve optimal utility when their responses are grounded in external knowledge sources. However, real-world documents, such as annual reports, scientific papers, and clinical guidelines, frequently combine extensive narrative content with complex, hierarchically structured tables. While existing retrieval-augmented generation (RAG) systems effectively integrate LLMs' generative capabilities with external retrieval-based information, their performance significantly deteriorates especially processing such heterogeneous text-table hierarchies. To address this limitation, we formalize the task of Heterogeneous Document RAG, which requires joint retrieval and reasoning across textual and hierarchical tabular data. We propose MixRAG, a novel three-stage framework: (i) hierarchy row-and-column-level (H-RCL) representation that preserves hierarchical structure and heterogeneous relationship, (ii) an ensemble retriever with LLM-based reranking for evidence alignment, and (iii) multi-step reasoning decomposition via a RECAP prompt strategy. To bridge the gap in available data for this domain, we release the dataset DocRAGLib, a 2k-document corpus paired with automatically aligned text-table summaries and gold document annotations. The comprehensive experiment results demonstrate that MixRAG boosts top-1 retrieval by 46% over strong text-only, table-only, and naive-mixture baselines, establishing new state-of-the-art performance for mixed-modality document grounding.

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。

↑