FT-RAG：一种面向复杂表格推理的细粒度检索增强生成框架
FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoning
AI总结：
FT-RAG通过细粒度检索和多模态融合提升表格推理能力，引入多表RAG库增强训练数据，实现表格和单元格命中率显著提升。
摘要：
检索增强生成（RAG）通过在推理过程中将响应与外部知识结合来增强大型语言模型（LLMs）。然而，传统RAG系统在结构化表格数据上表现不佳，主要由于粗粒度检索和对表格语义理解不足。为解决这些问题，我们引入FT-RAG，一种细粒度框架，通过将表格分解为条目级语义单元构建结构化图。FT-RAG采用结构邻居扩展机制在图检索中寻找语义连接实体，随后通过多模态融合整合表格检索结果的上下文。进一步，为应对该领域专用数据集稀缺问题，我们引入多表RAG库，包含9870个QA对，具有高复杂性和难度，旨在要求多表整合和文本-表格信息融合进行推理。FT-RAG在所有指标上均超越顶级基线，实现表格级和单元格级命中率分别提升23.5%和59.2%。生成性能也看到精确值准确率召回显著增加62.2%。这些指标验证了框架在纯表格和异构表格-文本上下文中的事实 grounding 有效性。因此，我们的方法在混合模态文档上的复杂推理中建立了新的最先进性能。
英文摘要：
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding responses in external knowledge during inference. However, conventiona RAG systems under-perform on structured tabular data, largely due to coarse retrieval granularity and insufficient table semantic comprehension. To address these limitations, we introduce FT-RAG, a fine-grained framework that employs knowledge association by decomposing tables into entry-level semantic units to construct a structured graph. FT-RAG employs a structural neighbor expansion mechanism to find semantically connected entities during graph retrieval, followed by multi-modal fusion to consolidate the context of table retrieval results. Further, to address the scarcity of specialized datasets in this domain, we introduce Multi-Table-RAG-Lib, a benchmark comprising 9870 QA pairs with high complexity and difficulty, curated to demand multi-table integration and text-table information fusion for reasoning. FT-RAG surpasses top-performing baselines across all metrics, achieving a 23.5\% and 59.2\% improvement in table-level and cell-level Hit Rates, respectively. Generation performance also sees a remarkable 62.2\% increase in exact value accuracy recall. These metrics verify the framework's effectiveness in factual grounding across both pure tabular and heterogeneous table-text contexts. Therefore, our method establishes a new state-of-the-art performance for complex reasoning over mixed-modality documents.
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。
