arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.15412cs.CL
收藏

面向幻灯片生成的文本到视觉迭代自验证方法

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

Shanghai Jiao Tong University(上海交通大学)

Yunqing Xu, Xinbei Ma, Jiyang Qiu, Hai Zhao

AI总结:

针对现有基于LLM的幻灯片生成智能体灵活性不足、缺乏自动优化机制的问题,将任务拆解为内容与布局生成,提出文本到视觉迭代自验证方法,在多项指标上显著优于基线。

摘要:

生成演示幻灯片是一项耗时的任务,迫切需要实现自动化。现有的基于大语言模型(LLM)的自主智能体灵活性有限,且缺乏自动化优化机制,在实际应用中受到限制。我们将缺失演示幻灯片的生成任务拆解为内容生成和布局生成两个核心模块,契合学术幻灯片的典型制作流程。首先,我们提出一种内容生成方法,通过融入相邻幻灯片的上下文并利用章节检索策略,提升内容的连贯性与相关性。在布局生成方面,我们提出一种文本到视觉的自验证流程,采用基于LLM的“评审器+优化器”工作流,将复杂的文本布局转换为直观的视觉格式。这种模态转换简化了任务,能够实现准确且类人的评审与优化。实验表明,我们的方法在一致性、逻辑流畅性、视觉吸引力和可读性方面均显著优于基线方法。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑