让AI从论文自动生成准确美观的科学图表，提升科研传播效率。
SciDoc2Diagrammer-MAF: Towards Generation of Scientific Diagrams from Documents guided by Multi-Aspect Feedback Refinement
- 通过中间代码生成，结合用户意图分步构建图表
- 多方面反馈机制使图表事实准确率与视觉质量显著提升
- 适合需要快速制作科研图示的研究者与科普作者
从学术论文自动生成科学图表可大幅节省制作教程、演示文稿和海报的时间，加速科研传播。现有文本到图像模型在处理长篇输入时难以生成准确且视觉美观的图表。我们提出新任务SciDoc2Diagram，旨在从论文中提取相关信息并生成图表，并构建了基准数据集SciDoc2DiagramBench。我们开发了多步骤管道SciDoc2Diagrammer，基于用户意图生成图表，过程中引入中间代码。初步结果显示，生成的图表常不完整或偏离原文，因此我们设计了多方面反馈精炼策略（MAF），显著提升了事实正确性与视觉吸引力，在自动评估与人工评分上均优于现有模型。
原文摘要 · Abstract (English)
Automating the creation of scientific diagrams from academic papers can significantly streamline the development of tutorials, presentations, and posters, thereby saving time and accelerating the process. Current text-to-image models struggle with generating accurate and visually appealing diagrams from long-context inputs. We propose SciDoc2Diagram, a task that extracts relevant information from scientific papers and generates diagrams, along with a benchmarking dataset, SciDoc2DiagramBench. We develop a multi-step pipeline SciDoc2Diagrammer that generates diagrams based on user intentions using intermediate code generation. We observed that initial diagram drafts were often incomplete or unfaithful to the source, leading us to develop SciDoc2Diagrammer-Multi-Aspect-Feedback (MAF), a refinement strategy that significantly enhances factual correctness and visual appeal and outperforms existing models on both automatic and human judgement.
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。