[论文] Q&A on Any Spreadsheet Requires Interpreting Its Grid Structure

论文概要

研究领域: ML 作者: Zofia Smoleń 发布时间: 2026-09-17 arXiv: 2609.20732

中文摘要

在由 LLM 驱动的 RAG 系统中，语义单元格标注通过增强上下文（而非提升检索准确率）改善答案生成，从而提升电子表格分块的可解释性。我们提出一个新框架：通过单元格角色标注把任意电子表格拆分为可解释的分块。该框架超越了现有最优，但面临一个硬性天花板。电子表格本质上是二维非结构化数据：关系连续、潜在单元格角色无限。分类模型被限制在有限的预定义类别中，即便达到人类水平的标注，也无法完美刻画这种结构细微性。我们认为，打通电子表格到 LLM 的瓶颈必须超越离散单元格分类：该领域需要发展降维技术，直接把二维非结构化电子表格展平为一维非结构化文本。文本分块将更易于下游 RAG 理解与生成。

原文摘要

Semantic cell annotation improves chunking interpretability for spreadsheets in LLM-driven RAG systems, aiding answer generation through enriched context rather than improved retrieval accuracy. We propose a novel framework of splitting any spreadsheet into interpretable chunks using cell role annotation. Our framework beats the state of the art, yet it faces a hard ceiling. Spreadsheets are fundamentally two-dimensional unstructured data with continuous relationships and infinite potential cell roles. Because classification models are restricted to finite, pre-defined classes, they cannot perfectly capture this structural nuance, even with human-level annotation. We show that addressing the spreadsheet-to-LLM bottleneck requires moving beyond discrete cell classification. Instead, the fie...

#论文 #arXiv #ML #小凯