用大模型自动设计表格布局，兼顾规则与视觉反馈。
SheetDesigner: MLLM-Powered Spreadsheet Layout Generation with Rule-Based and Vision-Based Reflection
- 结合规则与视觉反馈，用大模型生成表格元素位置
- 在3326张表格上测试，性能比基线高至少22.6%
- 适合需要快速生成结构化表格的开发者和数据工作者
电子表格在数据任务中至关重要，其丰富的结构化布局有助于高效传递信息。然而，手动设计表格耗时且需专业知识，亟需自动化方案。现有自动布局模型不适用于表格，主要因(1)将组件视为连续坐标下的轴对齐矩形，忽略表格固有的离散网格结构；(2)忽视数据依赖、上下文关联等独特语义关系。本文首次形式化表格布局生成任务，构建包含3,326张表格的数据集，并提出七项评估标准。我们提出SheetDesigner，一种无需训练的零样本框架，利用多模态大模型（MLLM）结合规则与视觉反思进行组件定位与内容填充。实验表明，该方法优于五种基线模型，性能提升至少22.6%。进一步发现，视觉模态能较好处理重叠与平衡，但在对齐方面表现不佳，需融合规则与视觉策略。代码与数据已开源。
原文摘要 · Abstract (English)
Spreadsheets are critical to data-centric tasks, with rich, structured layouts that enable efficient information transmission. Given the time and expertise required for manual spreadsheet layout design, there is an urgent need for automated solutions. However, existing automated layout models are ill-suited to spreadsheets, as they often (1) treat components as axis-aligned rectangles with continuous coordinates, overlooking the inherently discrete, grid-based structure of spreadsheets; and (2) neglect interrelated semantics, such as data dependencies and contextual links, unique to spreadsheets. In this paper, we first formalize the spreadsheet layout generation task, supported by a seven-criterion evaluation protocol and a dataset of 3,326 spreadsheets. We then introduce SheetDesigner, a zero-shot and training-free framework using Multimodal Large Language Models (MLLMs) that combines rule and vision reflection for component placement and content population. SheetDesigner outperforms five baselines by at least 22.6\%. We further find that through vision modality, MLLMs handle overlap and balance well but struggle with alignment, necessitates hybrid rule and visual reflection strategies. Our codes and data is available at Github.
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。