@inproceedings{wu-2024-uicoder,
title = "{UIC}oder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback",
author = "Wu, Jason and
Schoop, Eldon and
Leung, Alan and
Barik, Titus and
Bigham, Jeffrey and
Nichols, Jeffrey",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.417",
doi = "10.18653/v1/2024.naacl-long.417",
pages = "7511--7525",
abstract = "Many large language models (LLMs) struggle to consistently generate UI code that compiles and produces visually relevant designs. Existing approaches to improve generation rely either 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, and producing a new LLM by finetuning the original on the 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 results show the resulting models outperform all other downloadable baselines and approach the performance of larger proprietary models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wu-2024-uicoder">
<titleInfo>
<title>UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Eldon</namePart>
<namePart type="family">Schoop</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Leung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Titus</namePart>
<namePart type="family">Barik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeffrey</namePart>
<namePart type="family">Bigham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jeffrey</namePart>
<namePart type="family">Nichols</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many large language models (LLMs) struggle to consistently generate UI code that compiles and produces visually relevant designs. Existing approaches to improve generation rely either 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, and producing a new LLM by finetuning the original on the 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 results show the resulting models outperform all other downloadable baselines and approach the performance of larger proprietary models.</abstract>
<identifier type="citekey">wu-2024-uicoder</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.417</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.417</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>7511</start>
<end>7525</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback
%A Wu, Jason
%A Schoop, Eldon
%A Leung, Alan
%A Barik, Titus
%A Bigham, Jeffrey
%A Nichols, Jeffrey
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F wu-2024-uicoder
%X Many large language models (LLMs) struggle to consistently generate UI code that compiles and produces visually relevant designs. Existing approaches to improve generation rely either 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, and producing a new LLM by finetuning the original on the 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 results show the resulting models outperform all other downloadable baselines and approach the performance of larger proprietary models.
%R 10.18653/v1/2024.naacl-long.417
%U https://aclanthology.org/2024.naacl-long.417
%U https://doi.org/10.18653/v1/2024.naacl-long.417
%P 7511-7525
Markdown (Informal)
[UICoder: Finetuning Large Language Models to Generate User Interface Code through Automated Feedback](https://aclanthology.org/2024.naacl-long.417) (Wu et al., NAACL 2024)
ACL