Large Language Models (LLMs) have demonstrated remarkable skills across various design domains, including UI generation. However, current LLMs for UI generation tend to offer generic solutions that lack a deep understanding of task context and user preferences in specific scenarios. We present \textit{CrowdGenUI}, a framework that enhances LLM-driven UI generation with a crowdsourced user preference library. This approach addresses the limitations of existing methods by guiding LLM reasoning with user preferences, enabling the generation of UI widgets that align more closely with user needs and task-specific requirements. Using image editing as a test domain, we built this library from 50 users, capturing 720 user preferences, which include the predictability, efficiency, and explorability of multiple UI widgets. In a user study with 72 additional participants, our framework outperformed standard LLM-generated widgets in meeting user preferences and task requirements. We discuss these findings to inform future opportunities for designing user-centered and customizable UIs by comprehensively analyzing the extendability of the proposed framework and crowdsourced library.

翻译：大型语言模型（LLM）已在包括UI生成在内的多个设计领域展现出卓越能力。然而，当前用于UI生成的LLM往往提供通用解决方案，缺乏对特定场景中任务上下文和用户偏好的深入理解。本文提出\textit{CrowdGenUI}——一种通过众包用户偏好库增强LLM驱动UI生成的框架。该方法通过用户偏好引导LLM推理，解决了现有方法的局限性，从而生成更贴合用户需求与任务特定要求的UI组件。以图像编辑为测试领域，我们从50名用户构建了包含720条用户偏好的库，涵盖多种UI组件的可预测性、效率与可探索性。在72名额外参与者进行的用户研究中，本框架在满足用户偏好与任务需求方面优于标准LLM生成的组件。通过深入分析所提框架与众包库的可扩展性，我们讨论了这些发现对未来设计以用户为中心且可定制化UI的启示。