Textual-to-Visual Iterative Self-Verification for Slide Generation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916624827678720 |
|---|---|
| author | Xu, Yunqing Ma, Xinbei Qiu, Jiyang Zhao, Hai |
| author_facet | Xu, Yunqing Ma, Xinbei Qiu, Jiyang Zhao, Hai |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15412 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Textual-to-Visual Iterative Self-Verification for Slide Generation Xu, Yunqing Ma, Xinbei Qiu, Jiyang Zhao, Hai Computation and Language 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. |
| title | Textual-to-Visual Iterative Self-Verification for Slide Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.15412 |