mlsanityData to 14 Oct 2026

AlignUI: A Method for Designing LLM-Generated UIs Aligned with User Preferences

arXiv 2601.17614 ↗First posted 24 Jan 2026cs.HCcited by 2

On the map: LLM alignment / RLHF / preference optimisation → Diffusion and multimodal model alignment

Abstract (arXiv)

Designing user interfaces that align with user preferences is a time-consuming process, which requires iterative cycles of prototyping, user testing, and refinement. Recent advancements in LLM-based UI generation have enabled efficient UI generation to assist the UI design process. We introduce AlignUI, a method that aligns LLM-generated UIs with user tasks and preferences by using a user preference dataset to guide the LLM's reasoning process. The dataset was crowdsourced from 50 general users (the target users of generated UIs) and contained 720 UI control preferences on eight image-editing tasks. We evaluated AlignUI by generating UIs for six unseen tasks and conducting a user study with 72 additional general users. The results showed that the generated UIs closely align with multiple dimensions of user preferences. We conclude by discussing the applicability of our method to support user-aligned UI design for multiple task domains and user groups, as well as personalized user needs.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Diffusion and multimodal model alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 14 of its 65 references that are in the map. First posted on arXiv 24 Jan 2026.

Builds on

14 of 65 references.

References · 14

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2023Evaluating Large Language Models at Evaluating Instruction Followingcited by 302
  4. 2022Grounded Copilot: How Programmers Interact with Code-Generating Modelscited by 218
  5. 2019LayoutGAN: Generating Graphic Layouts with Wireframe Discriminatorscited by 131
  6. 2021Screen2Words: Automatic Mobile UI Summarization with Multimodal Learningcited by 120
  7. 2018FIRST: A Framework for Optimizing Information Quality in Mobile Crowdsensing Systemscited by 50
  8. 2024DynaVis: Dynamically Synthesized UI Widgets for Visualization Editingcited by 37
  9. 2018Machine Learning-Based Prototyping of Graphical User Interfaces for Mobile Appscited by 36
  10. 2025Generative and Malleable User Interfaces with Generative and Evolving Task-Driven Data Modelcited by 26
  11. 2025Leveraging Multimodal LLM for Inspirational User Interface Searchcited by 13
  12. 2024BISCUIT: Scaffolding LLM-Generated Code with Ephemeral UIs in Computational Notebookscited by 12
2 more
  1. 2025The GenUI Study: Exploring the Design of Generative UI Tools to Support UX Practitioners and Beyondcited by 9
  2. 2025TaskLens: Generating Task-Conditioned Scaffolded Interfaces for Learning Professional Creative Softwarecited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Efficient Personalization of Generative User Interfacescited by 0
  2. 2026SchemaGUI: A Schema-Driven Benchmark for Controllable GUI Generation Evaluationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024CrowdGenUI: Aligning LLM-Based UI Generation with Crowdsourced User Preferences
  2. 2025Improving User Interface Generation Models from Designer Feedback
  3. 2024UICrit: Enhancing Automated Design Evaluation with a UICritique Dataset
  4. 2025SpecifyUI: Supporting Iterative UI Design Intent Expression through Structured Specifications and Generative AI
  5. 2024Zero-Shot Prompting Approaches for LLM-based Graphical User Interface Generation
  6. 2024UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback
  7. 2025UI-UG: A Unified MLLM for UI Understanding and Generation
  8. 2025MLLM as a UI Judge: Benchmarking Multimodal LLMs for Predicting Human Perception of User Interfaces