PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides

TL;DR

PPTAgent is a novel system that automatically generates and evaluates presentations by analyzing reference slides, creating outlines, and iteratively editing slides, thereby improving content, design, and coherence.

Contribution

This paper introduces PPTAgent, a two-stage, edit-based approach for comprehensive presentation generation and PPTEval, a new evaluation framework assessing content, design, and coherence.

Findings

PPTAgent outperforms existing methods in content quality.

PPTAgent improves visual appeal and structural coherence.

PPTEval provides a holistic assessment of presentation quality.

Abstract

Automatically generating presentations from documents is a challenging task that requires accommodating content quality, visual appeal, and structural coherence. Existing methods primarily focus on improving and evaluating the content quality in isolation, overlooking visual appeal and structural coherence, which limits their practical applicability. To address these limitations, we propose PPTAgent, which comprehensively improves presentation generation through a two-stage, edit-based approach inspired by human workflows. PPTAgent first analyzes reference presentations to extract slide-level functional types and content schemas, then drafts an outline and iteratively generates editing actions based on selected reference slides to create new slides. To comprehensively evaluate the quality of generated presentations, we further introduce PPTEval, an evaluation framework that assesses presentations across three dimensions: Content, Design, and Coherence. Results demonstrate that PPTAgent significantly outperforms existing automatic presentation generation methods across all three dimensions.