Scientific figures clarity improves with AI but design still needs humans
Do You Miss the Nights We Spent Crafting Figures? Rethinking Teaser and Framework Figures in the Age of Generative AI
Computer Vision and Pattern Recognition
Summary
Scientists use pictures in papers to explain their ideas clearly. The authors studied hundreds of these pictures over time and tried improving them using AI while keeping the original meaning. They found AI can make figures easier to understand but sometimes less visually tidy. Their results suggest that AI can help researchers explore better designs, but people should still decide how to show information clearly and attractively.
What this means in practice
- •For scientific illustrators: Use AI tools to draft clearer research figures by adding explanation but refine visuals manually to maintain design quality.
- •For academic publishers: Implement AI-assisted review workflows to improve clarity of figures in submitted research while ensuring author control over visual style.
Authors
Xiaoqi Zhao, Youwei Pang, Kailai Zhou
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.