DesignLab: Designing Slides Through Iterative Detection and Correction
This addresses the problem of automated slide design for non-experts, though it appears incremental by building on existing tools with a novel decomposition approach.
The paper tackles the challenge of designing high-quality presentation slides for non-experts by proposing DesignLab, which uses an iterative loop of detection and correction roles to refine slides, outperforming existing methods including a commercial tool.
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.