GenGA: Editable and Data-Grounded Graphical Abstract Generation for Academic Papers

2026-08-05

AI Summary

Traditional approaches to graphical abstract generation produce raster images that are difficult to edit and fail to support the iterative demands of academic writing. This work proposes GenGA, a novel framework that formulates graphical abstract generation as an editable vector graphic synthesis task, directly producing a hierarchically structured set of vector elements from paper content, which can be edited at the element level in mainstream illustration software. We introduce the Structure Independence Coefficient (SIC) to quantitatively assess editability and develop an end-to-end system integrating vision–language models with vector graphic generation. Experiments demonstrate that GenGA surpasses existing methods in editability and outperforms human-created abstracts in conciseness and semantic alignment; furthermore, SIC strongly correlates with human editing effort.

Abstract

Graphical Abstracts (GAs) visually summarize the key findings of academic papers, playing a crucial role in facilitating the understanding of research content. Recently, advancements in vision-language models and image generation models have enabled the automatic generation of scientific figures based on paper content. However, most conventional methods output the generated results as raster graphics, making post-editing (e.g., text modification and layout changes) highly difficult. This poses a significant challenge, as they are unsuitable for the iterative figure revision process inherent in paper writing and peer review. To tackle these challenges, we define the novel task of generating editable GAs from paper content and propose GenGA, a new GA generation framework that directly produces figures in vector format. By generating figures as a collection of vector elements with a hierarchical structure, GenGA produces outputs that can be seamlessly imported into existing drawing tools for intuitive, element-level editing. Furthermore, we introduce the Structural Independence Coefficient (SIC), a metric that quantifies the editing simplicity of a figure based on the degree to which local modifications propagate to other elements. Experimental results show that GenGA achieves superior editing simplicity compared to conventional methods, and even surpasses human-authored GAs in conciseness and semantic alignment. We also validate SIC as an effective metric correlated with manual editing costs. This study fundamentally redefines GA generation as an editable vector graphic generation problem grounded in the practical workflows of researchers, significantly promoting effective scientific communication.

Problem

• Graphical Abstract
• editable vector graphics
• post-editing
• scientific communication
• figure revision

Innovation

• editable vector graphics
• graphical abstract generation
• Structural Independence Coefficient
• hierarchical vector representation
• scientific communication