SlidesGen-Bench: 通过计算和定量指标评估幻灯片生成
SlidesGen-Bench: Evaluating Slides Generation via Computational and Quantitative Metrics
AI总结：
SlidesGen-Bench通过计算和定量指标评估幻灯片生成，提出统一框架和可重复的量化指标，构建人类偏好对齐数据集，提升与人类判断的一致性。
摘要：
大型语言模型（LLMs）的快速发展催生了多样化的自动幻灯片生成范式，从代码驱动的布局到以图像为中心的合成。然而，评估这些异构系统仍然具有挑战性，因为现有协议往往难以在不同架构间提供可比评分，或依赖于未经校准的判断。在本文中，我们介绍了SlidesGen-Bench，一个旨在通过三个核心原则评估幻灯片生成的基准：通用性、量化和可靠性。首先，为了建立统一的评估框架，我们将分析基于视觉领域，将终端输出视为渲染结果，以保持对底层生成方法的中立。其次，我们提出了一种计算方法，通过三个不同的维度——内容、美观性和可编辑性——对幻灯片进行定量评估，提供可重复的指标，而以往的工作则依赖于主观或参考依赖的代理。最后，为了确保与人类偏好的高相关性，我们构建了Slides-Align1.5k数据集，一个覆盖九种主流生成系统在七种场景中幻灯片的人类偏好对齐数据集。我们的实验表明，SlidesGen-Bench在与人类判断的一致性方面优于现有评估流程。我们的代码和数据可在https://github.com/YunqiaoYang/SlidesGen-Bench获取。
英文摘要：
The rapid evolution of Large Language Models (LLMs) has fostered diverse paradigms for automated slide generation, ranging from code-driven layouts to image-centric synthesis. However, evaluating these heterogeneous systems remains challenging, as existing protocols often struggle to provide comparable scores across architectures or rely on uncalibrated judgments. In this paper, we introduce SlidesGen-Bench, a benchmark designed to evaluate slide generation through a lens of three core principles: universality, quantification, and reliability. First, to establish a unified evaluation framework, we ground our analysis in the visual domain, treating terminal outputs as renderings to remain agnostic to the underlying generation method. Second, we propose a computational approach that quantitatively assesses slides across three distinct dimensions - Content, Aesthetics, and Editability - offering reproducible metrics where prior works relied on subjective or reference-dependent proxies. Finally, to ensure high correlation with human preference, we construct the Slides-Align1.5k dataset, a human preference aligned dataset covering slides from nine mainstream generation systems across seven scenarios. Our experiments demonstrate that SlidesGen-Bench achieves a higher degree of alignment with human judgment than existing evaluation pipelines. Our code and data are available at https://github.com/YunqiaoYang/SlidesGen-Bench.
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。
