Generative UI: LLMs are Effective UI Generators
This addresses the long-standing promise of Generative UI for users needing dynamic, interactive interfaces from AI, though it is incremental as it builds on existing LLM capabilities.
The paper tackles the problem of LLMs producing static markdown outputs by demonstrating that properly prompted and tool-equipped modern LLMs can robustly generate high-quality custom UIs for any prompt, with human preferences overwhelmingly favoring these over standard markdown outputs and results being comparable to human experts in 50% of cases.
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 improvements from previous models. We also create and release PAGEN, a novel dataset of expert-crafted results to aid in evaluating Generative UI implementations, as well as the results of our system for future comparisons. Interactive examples can be seen at https://generativeui.github.io