用少量反馈实现个性化生成界面，效果优于传统方法。
Efficient Personalization of Generative User Interfaces
- 以设计师经验为先验，构建轻量级用户偏好模型。
- 在12位新设计师测试中，生成界面偏好度显著提升。
- 适合需要快速适配个体偏好的生成式UI系统开发者。
生成式用户界面（UI）可按需适应个人用户，但个性化困难，因理想界面属性主观、难以描述，且从稀疏反馈中推断成本高。我们通过新数据集研究此问题：20名训练设计师对600个生成的界面进行两两判断，直接分析偏好差异。发现设计师间分歧显著（平均kappa=0.25），书面理由显示，即使都强调层次或整洁等概念，其定义、优先级与应用方式仍不一致。基于此，我们提出一种样本高效个性化方法，将新用户表示为历史设计师的组合，而非固定设计概念规则。技术评估显示，该偏好模型优于预训练的UI评估器和更大规模的多模态模型，且随反馈增加表现更优。用于个性化生成时，其产出界面被12位新设计师更青睐，优于基线方法（包括直接用户提示）。结果表明，轻量级偏好收集可作为个性化生成式UI系统的实用基础。
原文摘要 · Abstract (English)
Generative user interfaces (UIs) create new opportunities to adapt interfaces to individual users on demand, but personalization remains difficult because desirable UI properties are subjective, hard to articulate, and costly to infer from sparse feedback. We study this problem through a new dataset in which 20 trained designers each provide pairwise judgments over the same 600 generated UIs, enabling direct analysis of preference divergence. We find substantial disagreement across designers (average kappa = 0.25), and written rationales reveal that even when designers appeal to similar concepts such as hierarchy or cleanliness, designers differ in how they define, prioritize, and apply those concepts. Motivated by these findings, we develop a sample-efficient personalization method that represents a new user in terms of prior designers rather than a fixed rubric of design concepts. In a technical evaluation, our preference model outperforms both a pretrained UI evaluator and a larger multimodal model, and scales better with additional feedback. When used to personalize generation, it also produces interfaces preferred by 12 new designers over baseline approaches, including direct user prompting. Our findings suggest that lightweight preference elicitation can serve as a practical foundation for personalized generative UI systems.
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。