UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909222156894208 |
|---|---|
| author | Wu, Jason Schoop, Eldon Leung, Alan Barik, Titus Bigham, Jeffrey P. Nichols, Jeffrey |
| author_facet | Wu, Jason Schoop, Eldon Leung, Alan Barik, Titus Bigham, Jeffrey P. Nichols, Jeffrey |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_07739 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback Wu, Jason Schoop, Eldon Leung, Alan Barik, Titus Bigham, Jeffrey P. Nichols, Jeffrey Computation and Language Human-Computer Interaction Software Engineering 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. |
| title | UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback |
| topic | Computation and Language Human-Computer Interaction Software Engineering |
| url | https://arxiv.org/abs/2406.07739 |