发表机构
Purdue University; Duke Kunshan University（普渡大学; 杜克昆山大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
GUIDE是一个设计师参与循环的系统，通过提示优化和自适应合规性评分模型，使生成式用户界面持续符合设计意图，并在评估中优于基线。
AI 中文摘要
生成式用户界面（GenUIs）使应用程序能够根据用户需求和上下文按需生成界面。与传统用户界面一样，它们仍必须反映设计师的意图并符合品牌标识等要求。与传统用户界面不同，设计师无法直接指定或查看GenUI可能生成的每一个界面，这使得设计意图更难执行。我们介绍了GUIDE（GenUI开发环境），这是一个让设计师在创建和编辑界面时持续检查和优化GenUI行为的系统。GUIDE通过提示优化和新颖的自适应合规性评分模型，利用设计师的修改和交互来调整GenUI。我们验证了GUIDE的评分模型和系统。在真实与合成应用屏幕的保留比较中，该评分模型匹配或超越了专有的LLM基线。在一项涉及12名UI/UX从业者的研究中，参与者认为GUIDE有效且可用，并显著偏好其对齐输出，优于使用示例和模型生成此http URL的强基线。
英文摘要
Generative User Interfaces (GenUIs) enable applications to generate interfaces on demand from user needs and context. Like conventional UIs, they must still reflect designers' intent and conform to requirements such as brand identity. Unlike conventional UIs, designers cannot directly specify or see every interface a GenUI may produce, making design intent harder to enforce. We introduce GUIDE (GenUI Development Environment), a system that lets designers continuously inspect and refine GenUI behavior as they create and edit interfaces. GUIDE uses designers' modifications and interactions to adapt GenUIs through prompt optimization and a novel adaptive conformance scoring model. We validate GUIDE's scoring model and system. The scoring model matched or outperformed proprietary LLM baselines on held-out comparisons of real and synthetic application screens. In a study with 12 UI/UX practitioners, participants found GUIDE effective and usable and significantly preferred aligned outputs over a strong baseline using exemplars and a model-generated design.md.
Comments24 pages, 13 figures, 5 tables
