CLAIMay 2

FT-RAG: A Fine-grained Retrieval-Augmented Generation Framework for Complex Table Reasoning

arXiv:2605.0149536.8h-index: 6
AI Analysis

This work addresses the underperformance of RAG on structured tabular data, providing a new state-of-the-art for complex reasoning over mixed-modality documents.

FT-RAG introduces a fine-grained retrieval-augmented generation framework that decomposes tables into entry-level semantic units and uses structural neighbor expansion for graph retrieval, achieving 23.5% and 59.2% improvement in table-level and cell-level Hit Rates, and 62.2% increase in exact value accuracy recall over baselines.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes