跳转至

TabScope：面向表格问答的问题自适应范围选择

文章背景与核心概要

随着表格规模的不断增大，大语言模型（LLMs）在处理表格问答任务时往往会出现性能下降，但这种性能降幅会因问题类型的不同而有所差异。定位敏感型问题容易受到不相关数据的干扰，而更广泛的查询则仍然受益于全表推理。

为了解决这一问题，本文介绍了 TabScope 框架，这是一种能够在局部推理和全表推理模式之间进行动态切换的问题自适应框架。通过将“操作感知表格分解”与“问题类型预测”相结合，该框架能够高效构建子表以优化准确率。在 WikiTQ 和新推出的 SLQA 基准测试上的实验表明，明确“何时”进行定位与明确“如何”进行定位同样重要。

TabScope：面向表格问答的问题自适应范围选择

TabScope: Question-Adaptive Scope Selection for Table Question Answering

摘要

大语言模型（LLMs）在表格问答任务中表现出强劲的性能，然而随着表格规模的增大，它们的准确率往往会下降。我们发现，这种性能下降在不同问题类型中并不均匀。定位敏感型问题尤其受到不相关表格内容的负面影响，而需要更广泛证据的问题则可能依然受益于全表推理。

基于这一观察，我们提出了一种在局部推理和全表推理之间进行动态选择的问题自适应框架。该框架通过操作感知的表格分解构建特定于问题的子表，并利用预测出的问题类型来确定合适的推理模式。我们进一步引入了用于评估证据选择的银标准参考子表，并构建了基于真实世界长表格的基准测试 SLQA。在 WikiTQ 和 SLQA 上的实验表明，局部化对于查找和局部推理问题特别有效，而在局部推理和全表推理之间进行自适应选择能够实现最佳的整体性能。这些结果凸显出，长表格问答不仅需要决定如何进行局部化，还需要决定何时进行局部化。

Abstract

Large Language Models (LLMs) have shown strong performance on table question answering, yet their accuracy often degrades as table size increases. We find that this degradation is not uniform across question types. Localization-sensitive questions are particularly affected by irrelevant table content, while questions requiring broader evidence may still benefit from full-table reasoning.

Based on this observation, we propose a question-adaptive framework that dynamically selects between localized and full-table reasoning. The framework constructs question-specific sub-tables through operation-aware table decomposition and uses the predicted question type to determine the appropriate reasoning mode. We further introduce silver reference sub-tables for evaluating evidence selection and construct SLQA, a benchmark based on real-world long tables. Experiments on WikiTQ and SLQA show that localization is particularly effective for lookup and local reasoning questions, while adaptive selection between localized and full-table reasoning achieves the best overall performance. These results highlight that long-table QA requires deciding not only how to localize, but also when to localize.

论文元数据

Paper Metadata

字段 (Field) 详情 (Details)
标题 (Title) TabScope: Question-Adaptive Scope Selection for Table Question Answering
作者 (Authors) Yuxiang Wang, Junhao Gan, Jianzhong Qi
提交时间 (Submitted) 2026年9月3日 (September 3, 2026)
主学科 (Primary Subject) 计算与语言 (cs.CL)
辅学科 (Secondary Subjects) 人工智能 (cs.AI)
引用方式 (Cite As) arXiv:2609.03395 [cs.CL]
DOI 10.48550/arXiv.2609.03395
许可协议 (License) 知识共享署名 4.0 国际版 license icon

访问与资源

Access & Resources