Large language models (LLMs) struggle to consistently generate UI code that compiles and produces visually relevant designs. Existing approaches to improve generation rely on expensive human feedback or distilling a proprietary model. In this paper, we explore the use of automated feedback (compilers and multi-modal models) to guide LLMs to generate high-quality UI code. Our method starts with an existing LLM and iteratively produces improved models by self-generating a large synthetic dataset using an original model, applying automated tools to aggressively filter, score, and de-duplicate the data into a refined higher quality dataset. The original LLM is improved by finetuning on this refined dataset. We applied our approach to several open-source LLMs and compared the resulting performance to baseline models with both automated metrics and human preferences. Our evaluation shows the resulting models outperform all other downloadable baselines and approach the performance of larger proprietary models.

翻译：大型语言模型（LLMs）难以持续生成可编译且具有视觉相关设计的用户界面代码。现有改进生成的方法依赖于昂贵的人工反馈或蒸馏专有模型。本文探索利用自动化反馈（编译器与多模态模型）引导LLMs生成高质量用户界面代码。我们的方法从现有LLM出发，通过使用原始模型自生成大规模合成数据集，应用自动化工具对数据进行积极过滤、评分和去重，最终提炼出更高质量的数据集，从而迭代产生改进模型。原始LLM通过在该精炼数据集上进行微调得到优化。我们将该方法应用于多个开源LLM，并通过自动化指标和人工偏好将其性能与基线模型进行比较。评估结果表明，生成的模型优于所有其他可下载的基线模型，性能接近更大的专有模型。