Efficient Personalization of Generative User Interfaces
cs.LG, cs.AI, cs.CV, cs.HC
Submitted: 2026-04-10
Updated: 2026-09-14
License: http://creativecommons.org/licenses/by/4.0/
The gist: Generative user interfaces (GenUIs) create new opportunities to adapt interfaces to individual users on demand.
Terminology
Abstract
Generative user interfaces (GenUIs) create new opportunities to adapt interfaces to individual users on demand. Yet personalization is difficult because it is not possible to provide settings for screens that have not yet been generated, making it necessary to learn preferences from users' feedback on generated interfaces. Such feedback is sparse, subjective, and often difficult to articulate. We study this problem through a new dataset in which 20 participants each judge the same 600 pairs of GenUIs. Their judgments differ substantially (Krippendorff's alpha = 0.25), and written rationales show that even when participants consider similar UI properties, such as color tone or hierarchy, they often make different choices and prioritize them differently. We develop a sample-efficient personalization method that uses a few pairwise judgments to weight prior users' preferences rather than relying on a fixed rubric of UI attributes. Our method outperforms a pretrained UI evaluator and a larger multimodal model offline. In an online study with 12 new users, participants preferred interfaces personalized by our method over all baselines, including shared guidelines and users' own written preferences.
Sources
- User Embedding Model for Personalized Language Prompting
- Can LLM be a Personalized Judge?
- Do MLLMs Capture How Interfaces Guide User Behavior? A Benchmark for Multimodal UI/UX Design Understanding
- Capturing Individual Human Preferences with Reward Features
- Personalized Recommendations via Active Utility-based Pairwise Sampling
- Generative Interfaces for Language Models
- SpecifyUI: Supporting Iterative UI Design Intent Expression through Structured Specifications and Generative AI
- DesignPref: Capturing Personal Preferences in Visual Design Generation
- Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
- Reaching Beyond the Mode: RL for Distributional Reasoning in Language Models
- Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
- Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF
- Llama 2: Open Foundation and Fine-Tuned Chat Models
- From 1,000,000 Users to Every User: Scaling Up Personalized Preference for User-level Alignment
- AesBiasBench: Evaluating Bias and Alignment in Multimodal Language Models for Personalized Image Aesthetic Assessment
- PrefPalette: Personalized Preference Modeling with Latent Attributes
- Personalized Language Modeling from Personalized Human Feedback
- MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces
- Comparison-based Active Preference Learning for Multi-dimensional Personalization
- Inference-Time Personalized Alignment with a Few User Preference Queries
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks