让大模型不仅生成内容，还能自动设计出美观的界面。
Generative UI: LLMs are Effective UI Generators
- 用提示词和工具组合，让大模型自动生成定制化界面。
- 人类更偏好生成界面，虽不如专家设计但50%情况下相当。
- 提出新数据集PAGEN，支持未来界面生成评估。
AI模型擅长生成内容，但通常以静态、预设的界面呈现，如纯文本的markdown输出。生成式用户界面（Generative UI）曾是长期愿景，即模型不仅能生成内容，还能自动生成相应界面。此前该能力难以稳定实现。本文展示，通过恰当提示与工具配置，现代大语言模型可稳健生成高质量、个性化的用户界面，适用于绝大多数提示。忽略生成速度，人类对生成界面的满意度远超标准文本输出；尽管仍不及人类专家设计，但在50%的情况下表现相当。该能力具有涌现特性，相比以往模型有显著提升。同时，我们创建并发布全新数据集PAGEN，包含专家手工设计的界面结果，用于评估生成式界面系统，并公开了本系统的生成结果以供未来比较。交互示例见https://generativeui.github.io
原文摘要 · Abstract (English)
AI models excel at creating content, but typically render it with static, predefined interfaces. Specifically, the output of LLMs is often a markdown "wall of text". Generative UI is a long standing promise, where the model generates not just the content, but the interface itself. Until now, Generative UI was not possible in a robust fashion. We demonstrate that when properly prompted and equipped with the right set of tools, a modern LLM can robustly produce high quality custom UIs for virtually any prompt. When ignoring generation speed, results generated by our implementation are overwhelmingly preferred by humans over the standard LLM markdown output. In fact, while the results generated by our implementation are worse than those crafted by human experts, they are at least comparable in 50% of cases. We show that this ability for robust Generative UI is emergent, with substantial improvements from previous models. We also create and release PAGEN, a novel dataset of expert-crafted results to aid in evaluating Generative UI implementations, as well as the results of our system for future comparisons. Interactive examples can be seen at https://generativeui.github.io
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。