用图结构保留表格关系，提升大模型问答准确率
Beyond Linearization: Attributed Table Graphs for Table Reasoning
- 将表格转为带属性的图结构，显式保持行列单元格关系
- 在多个基准上最高提升9.7%准确率，克服信息丢失问题
- 无需额外训练，适合需要精准推理的表格问答场景
表格推理是基于表格数据回答问题的重要任务。当前方法普遍将表格线性化为文本输入大语言模型（LLM），但这种方式需模型自行推断行列单元格关系，导致证据路径难追踪，并存在'中间信息丢失'问题。为此，我们提出表图推理器（TabGR），将表格表示为不依赖任务训练的属性表图（ATG），显式保留行列单元格结构，并支持可追溯的图推理。进一步提出基于问题引导的个性化页面排名（QG-PPR）机制，重新排序表中数据以缓解信息丢失。在多个表格推理基准上的实验表明，TabGR在准确率上持续优于现有最优模型，最高提升达9.7%。代码已开源：https://github.com/yxw-11/TabGR。
原文摘要 · Abstract (English)
Table reasoning, a task to answer questions by reasoning over data presented in tables, is an important topic due to the prevalence of knowledge stored in tabular formats. Recent solutions use Large Language Models (LLMs) for their semantic understanding and reasoning capabilities. A common paradigm of such solutions linearizes tables to form plain texts that are served as input to LLMs. This paradigm has critical issues. It requires LLMs to infer row-column-cell relations from serialized inputs, makes evidence paths harder to trace, and is subject to the "lost-in-the-middle" issue. To address these issues, we propose Table Graph Reasoner (TabGR), a model that represents tables as an Attributed Table Graph (ATG) without task-specific training. The ATG explicitly preserves row-column-cell structure while enabling graph-based reasoning over traceable evidence paths. We further propose a Question-Guided Personalized PageRank (QG-PPR) mechanism to rerank tabular data and mitigate the lost-in-the-middle issue. Extensive experiments across multiple table reasoning benchmarks show that TabGR consistently outperforms state-of-the-art models by up to 9.7% in accuracy. Our code is available at: https://github.com/yxw-11/TabGR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。