arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2604.09577cs.HCcs.AIcs.CLcs.LG
收藏

生成用户界面:LLM在生成用户界面方面非常有效

Generative UI: LLMs are Effective UI Generators

Google Research(谷歌研究院)
Yaniv Leviathan, Dani Valevski, Matan Kalman, Danny Lumen, Eyal Segalis, Eyal Molad, Shlomi Pasternak, Vishnu Natchu, Valerie Nygaard, Srinivasan, Venkatachary,… 展开作者

Yaniv Leviathan, Dani Valevski, Matan Kalman, Danny Lumen, Eyal Segalis, Eyal Molad, Shlomi Pasternak, Vishnu Natchu, Valerie Nygaard, Srinivasan, Venkatachary, James Manyika, Yossi Matias

AI总结:

本文提出生成用户界面的概念,展示通过适当提示和工具,现代LLM能生成高质量的定制UI。尽管生成速度不计,人类更偏好其输出,且在50%的情况下与专家相当。同时发布PAGEN数据集以评估生成用户界面的实现。

摘要:

AI模型在创建内容方面表现出色,但通常以静态、预定义的界面呈现。具体而言,LLM的输出通常是markdown的“文本墙”。生成用户界面是一个长期存在的承诺,其中模型不仅生成内容,还生成界面本身。迄今为止,生成用户界面无法以稳健的方式实现。我们证明,当正确提示并配备适当工具时,现代LLM能够稳健地为几乎所有提示生成高质量的定制UI。忽略生成速度,我们实现的结果在人类中 overwhelmingly 更受欢迎于标准LLM的markdown输出。事实上,尽管我们实现的结果比人类专家手工制作的结果差,但在50%的情况下至少相当。我们展示这种稳健的生成用户界面能力是涌现的,与先前模型有显著改进。我们还创建并发布了PAGEN,一个由专家手工制作的结果组成的新型数据集,以帮助评估生成用户界面的实现,以及我们系统的结果以供未来比较。交互示例可在https://generativeui.github.io查看。

英文摘要:

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

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。

↑