DesignLab：通过迭代检测与修正进行幻灯片设计

摘要

对于非专业人士而言，设计高质量的演示文稿幻灯片颇具挑战，这源于在众多设计选项中做出选择的复杂性。尽管众多自动化工具能够提供布局与配色方案的建议，但它们往往缺乏对自身输出进行优化的能力，而这在实际工作流程中至关重要。我们提出了DesignLab，它将设计过程分解为两个角色：设计评审者，负责识别设计相关问题；以及设计贡献者，负责修正这些问题。这种分解形成了一个迭代循环，评审者持续发现问题，贡献者则不断修正，使得草稿在每次迭代中得以进一步打磨，最终达到原本难以企及的质量水平。我们针对这两个角色对大型语言模型进行了微调，并通过引入受控扰动来模拟中间草稿，使设计评审者学会识别设计错误，贡献者学会如何修正。实验结果表明，DesignLab通过拥抱设计的迭代本质，能够生成更为精致、专业的幻灯片，其表现优于现有的设计生成方法，包括一款商业工具。

English

Designing high-quality presentation slides can be challenging for non-experts due to the complexity involved in navigating various design choices. Numerous automated tools can suggest layouts and color schemes, yet often lack the ability to refine their own output, which is a key aspect in real-world workflows. We propose DesignLab, which separates the design process into two roles, the design reviewer, who identifies design-related issues, and the design contributor who corrects them. This decomposition enables an iterative loop where the reviewer continuously detects issues and the contributor corrects them, allowing a draft to be further polished with each iteration, reaching qualities that were unattainable. We fine-tune large language models for these roles and simulate intermediate drafts by introducing controlled perturbations, enabling the design reviewer learn design errors and the contributor learn how to fix them. Our experiments show that DesignLab outperforms existing design-generation methods, including a commercial tool, by embracing the iterative nature of designing which can result in polished, professional slides.

DesignLab：通过迭代检测与修正进行幻灯片设计

DesignLab: Designing Slides Through Iterative Detection and Correction

摘要

Support