Textual-to-Visual Iterative Self-Verification for Slide Generation

TL;DR

This paper presents a novel method for automating slide generation by combining content coherence enhancement with a textual-to-visual self-verification process, improving slide quality and relevance.

Contribution

It introduces a two-step approach with context-aware content generation and a self-verification workflow for layout refinement, advancing the automation of slide creation.

Findings

Outperforms baseline methods in alignment and logical flow

Enhances visual appeal and readability of generated slides

Demonstrates significant improvements in slide quality

Abstract

Generating presentation slides is a time-consuming task that urgently requires automation. Due to their limited flexibility and lack of automated refinement mechanisms, existing autonomous LLM-based agents face constraints in real-world applicability. We decompose the task of generating missing presentation slides into two key components: content generation and layout generation, aligning with the typical process of creating academic slides. First, we introduce a content generation approach that enhances coherence and relevance by incorporating context from surrounding slides and leveraging section retrieval strategies. For layout generation, we propose a textual-to-visual self-verification process using a LLM-based Reviewer + Refiner workflow, transforming complex textual layouts into intuitive visual formats. This modality transformation simplifies the task, enabling accurate and human-like review and refinement. Experiments show that our approach significantly outperforms baseline methods in terms of alignment, logical flow, visual appeal, and readability.