TL;DR
This paper demonstrates that with proper prompting and tools, modern LLMs can reliably generate high-quality, custom user interfaces for a wide range of prompts, surpassing standard markdown outputs in human preference.
Contribution
It introduces a robust method for LLMs to generate user interfaces, showing emergent capabilities and releasing PAGEN, a dataset for evaluating Generative UI systems.
Findings
Generated UIs are preferred by humans over markdown outputs.
Results are comparable to human-crafted UIs in 50% of cases.
Substantial improvements over previous models in Generative UI ability.
Abstract
AI models excel at creating content, but typically render it with static, predefined interfaces. Specifically, the output of LLMs is often a markdown "wall of text". Generative UI is a long standing promise, where the model generates not just the content, but the interface itself. Until now, Generative UI was not possible in a robust fashion. We demonstrate that when properly prompted and equipped with the right set of tools, a modern LLM can robustly produce high quality custom UIs for virtually any prompt. When ignoring generation speed, results generated by our implementation are overwhelmingly preferred by humans over the standard LLM markdown output. In fact, while the results generated by our implementation are worse than those crafted by human experts, they are at least comparable in 50% of cases. We show that this ability for robust Generative UI is emergent, with substantial…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
