你还怀念我们一起打磨图表的夜晚吗？生成式AI时代重新审视Teaser图与框架图
Do You Miss the Nights We Spent Crafting Figures? Rethinking Teaser and Framework Figures in the Age of Generative AI
Xiaoqi Zhao · Youwei Pang · Kailai Zhou
中文摘要
科学图表通过抽象、构图与强调的选择，将研究想法赋予视觉形式。生成式AI为实现这些选择提供了新途径，也引发了对解释清晰度与有目的视觉表达的疑问。通过对200篇论文中371幅动机图与框架图的视觉回顾来考察这些问题。语料库包含按配额抽取的主样本160篇论文，跨越四个时间段，以及另设的40篇目的性风格对比样本。单一多模态评判器评估沟通与设计的六个维度，每幅图重复评判三次。尝试对全部371幅图进行源约束修订，其中369幅通过记录的保真度检查。原始图表评分在各时间段间未呈现一致下降。修订使平均清晰度评分提高0.428分，审美连贯性评分下降0.111分（五分制）。六维平均分的提升在主样本的动机图上大于框架图。案例分析表明，增加解释可以厘清比较，但排版层级与视觉经济性仍未解决。这些基于模型的发现支持研究者主导的设计，AI辅助探索，作者保留对解释目的、构图与科学关系的责任。配套图谱与评估记录见 https://ntu-ai4x.github.io/Rethinking_Figures/index_en.html。
关键要点
- 01分析200篇论文的371幅动机图与框架图，含160篇主样本与40篇风格对比样本
- 02多模态评判器评估六维度，每图重复三次，369幅修订图通过保真度检查
- 03修订使清晰度提高0.428分、审美连贯性下降0.111分（五分制）
- 04动机图的六维平均提升大于框架图，增加解释未解决排版层级与视觉经济性
- 05结论支持研究者主导设计，AI辅助探索，作者保留解释与构图责任
解读
尚无解读。
原始英文摘要
arXiv:2611.08486v1 Announce Type: new Abstract: Scientific figures give research ideas a visual form through choices of abstraction, composition, and emphasis. Generative AI offers new ways to realize these choices, raising questions about explanatory clarity and purposeful visual expression. We examine these questions through a visual retrospective of 371 motivation and framework figures from 200 papers. The corpus comprises a quota-based main sample of 160 papers spanning four temporal periods and a separate purposive style-contrast sample of 40 papers. A single multimodal judge evaluates six dimensions of communication and design, with three repeated judgments per figure. We attempt source-constrained revisions of all 371 figures, of which 369 pass the recorded fidelity checks. Original-figure ratings show no uniform decline across periods. Revisions increase mean clarity ratings by 0.428 points and decrease aesthetic coherence ratings by 0.111 points on a five-point scale. Gains in the six-dimension average are larger for main-sample motivation figures than for frameworks. Case analyses show that added explanation can clarify comparisons while leaving typographic hierarchy and visual economy unresolved. These model-based findings support researcher-led design, with AI assisting exploration and authors retaining responsibility for explanatory purpose, composition, and scientific relationships. The accompanying atlas and evaluation records are available at https://ntu-ai4x.github.io/Rethinking_Figures/index_en.html.