DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models

The rise of Large Language Models (LLMs) has streamlined frontend interface creation through tools like Vercel's v0, yet surfaced challenges in design quality (e.g., accessibility, and usability). Current solutions, often limited by their focus, generalisability, or data dependency, fall short...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Proceedings / International Conference on Software Engineering s. 2483 - 2494
Hlavní autoři: Yuan, Mingyue, Chen, Jieshan, Xing, Zhenchang, Quigley, Aaron, Luo, Yuyu, Luo, Tianqi, Mohammadi, Gelareh, Lu, Qinghua, Zhu, Liming
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 26.04.2025
Témata:
ISSN:1558-1225
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract The rise of Large Language Models (LLMs) has streamlined frontend interface creation through tools like Vercel's v0, yet surfaced challenges in design quality (e.g., accessibility, and usability). Current solutions, often limited by their focus, generalisability, or data dependency, fall short in addressing these complexities. Moreover, none of them examine the quality of LLM-generated UI design. In this work, we introduce DesignRepair, a novel dual-stream design guideline-aware system to examine and repair the UI design quality issues from both code aspect and rendered page aspect. We utilised the mature and popular Material Design as our knowledge base to guide this process. Specifically, we first constructed a comprehensive knowledge base encoding Google's Material Design principles into low-level component knowledge base and high-level system design knowledge base. After that, DesignRepair employs a LLM for the extraction of key components and utilizes the Playwright tool for precise page analysis, aligning these with the established knowledge bases. Finally, we integrate Retrieval-Augmented Generation with state-of-the-art LLMs like GPT-4 to holistically refine and repair frontend code through a strategic divide and conquer approach. Our extensive evaluations validated the efficacy and utility of our approach, demonstrating significant enhancements in adherence to design guidelines, accessibility, and user experience metrics.
AbstractList The rise of Large Language Models (LLMs) has streamlined frontend interface creation through tools like Vercel's v0, yet surfaced challenges in design quality (e.g., accessibility, and usability). Current solutions, often limited by their focus, generalisability, or data dependency, fall short in addressing these complexities. Moreover, none of them examine the quality of LLM-generated UI design. In this work, we introduce DesignRepair, a novel dual-stream design guideline-aware system to examine and repair the UI design quality issues from both code aspect and rendered page aspect. We utilised the mature and popular Material Design as our knowledge base to guide this process. Specifically, we first constructed a comprehensive knowledge base encoding Google's Material Design principles into low-level component knowledge base and high-level system design knowledge base. After that, DesignRepair employs a LLM for the extraction of key components and utilizes the Playwright tool for precise page analysis, aligning these with the established knowledge bases. Finally, we integrate Retrieval-Augmented Generation with state-of-the-art LLMs like GPT-4 to holistically refine and repair frontend code through a strategic divide and conquer approach. Our extensive evaluations validated the efficacy and utility of our approach, demonstrating significant enhancements in adherence to design guidelines, accessibility, and user experience metrics.
Author Chen, Jieshan
Luo, Yuyu
Mohammadi, Gelareh
Lu, Qinghua
Zhu, Liming
Quigley, Aaron
Luo, Tianqi
Xing, Zhenchang
Yuan, Mingyue
Author_xml – sequence: 1
  givenname: Mingyue
  surname: Yuan
  fullname: Yuan, Mingyue
  email: mingyue.yuan@unsw.edu.au
  organization: University of New South Wales,Australia
– sequence: 2
  givenname: Jieshan
  surname: Chen
  fullname: Chen, Jieshan
  email: jieshan.chen@data61.csiro.au
  organization: CSIRO's Data61,Australia
– sequence: 3
  givenname: Zhenchang
  surname: Xing
  fullname: Xing, Zhenchang
  email: zhenchang.xing@data61.csiro.au
  organization: CSIRO's Data61,Australia
– sequence: 4
  givenname: Aaron
  surname: Quigley
  fullname: Quigley, Aaron
  email: a.quigley@data61.csiro.au
  organization: University of New South Wales,Australia
– sequence: 5
  givenname: Yuyu
  surname: Luo
  fullname: Luo, Yuyu
  email: yuyuluo@hkust-gz.edu.cn
  organization: The Hong Kong University of Science and Technology,(Guangzhou),China
– sequence: 6
  givenname: Tianqi
  surname: Luo
  fullname: Luo, Tianqi
  email: tluo553@hkust-gz.edu.cn
  organization: The Hong Kong University of Science and Technology,(Guangzhou),China
– sequence: 7
  givenname: Gelareh
  surname: Mohammadi
  fullname: Mohammadi, Gelareh
  email: g.mohammadi@unsw.edu.au
  organization: University of New South Wales,Australia
– sequence: 8
  givenname: Qinghua
  surname: Lu
  fullname: Lu, Qinghua
  email: qinghua.lu@data61.csiro.au
  organization: University of New South Wales,Australia
– sequence: 9
  givenname: Liming
  surname: Zhu
  fullname: Zhu, Liming
  email: liming.zhu@data61.csiro.au
  organization: University of New South Wales,Australia
BookMark eNotUMtOwzAQNAgk2tI_6ME_kLJ-bBxzq_qiUhAShROHykm2wah1KydRxd8TqVxmVvPYwwzZXTgFYmwiYCoE2KfNfLtEVNpMJUicAvTiDRtbYzOlBAKmVtyygUDMEiElPrBh0_wAQKqtHbCvBTW-Du90dj4-80XnDsm2jeSO_OrwdecrOvhAyeziIvFVPIWWQsWvHX7x7TfPXaypx1B3rj9eT32leWT3e3doaPzPI_a5Wn7MX5L8bb2Zz_LEyRTaREoq9qVOoXLCFCoDjakoVQqysBUZ0hZLp5FAWFMUfVjqMnOVwUobh6pUIza5_vVEtDtHf3Txd9evo0DKTP0BC1BVMQ
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IH
CBEJK
RIE
RIO
DOI 10.1109/ICSE55347.2025.00109
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Proceedings Order Plan (POP) 1998-present by volume
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP) 1998-present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 9798331505691
EISSN 1558-1225
EndPage 2494
ExternalDocumentID 11030228
Genre orig-research
GroupedDBID -~X
.4S
.DC
29O
5VS
6IE
6IF
6IH
6IK
6IL
6IM
6IN
8US
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
ARCSS
AVWKF
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
EDO
FEDTE
I-F
IEGSK
IJVOP
IPLJI
M43
OCL
RIE
RIL
RIO
ID FETCH-LOGICAL-a260t-22ebfc460da17b3804561c3602b9de7e495ca45e0197bb2eb24c8ad75d47a53c3
IEDL.DBID RIE
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001538318100194&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Aug 27 01:40:27 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-a260t-22ebfc460da17b3804561c3602b9de7e495ca45e0197bb2eb24c8ad75d47a53c3
PageCount 12
ParticipantIDs ieee_primary_11030228
PublicationCentury 2000
PublicationDate 2025-April-26
PublicationDateYYYYMMDD 2025-04-26
PublicationDate_xml – month: 04
  year: 2025
  text: 2025-April-26
  day: 26
PublicationDecade 2020
PublicationTitle Proceedings / International Conference on Software Engineering
PublicationTitleAbbrev ICSE
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0006499
Score 2.2896473
Snippet The rise of Large Language Models (LLMs) has streamlined frontend interface creation through tools like Vercel's v0, yet surfaced challenges in design quality...
SourceID ieee
SourceType Publisher
StartPage 2483
SubjectTerms Codes
Design Guideline
Design methodology
Frontend Code Repair
Knowledge based systems
Large language models
Maintenance engineering
Software development management
Software engineering
System analysis and design
UI Design
Usability
User experience
Title DesignRepair: Dual-Stream Design Guideline-Aware Frontend Repair with Large Language Models
URI https://ieeexplore.ieee.org/document/11030228
WOSCitedRecordID wos001538318100194&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JS8NAGB1s8eCpLhV35uB1bDJLJvEmXVQopaBCwUOZ5QsUaippo3_fmUmsXjx4CSELgRky877lvYfQtRYyy6nX2M-pJlymhmgDlkgjKVVSCKWCiOtYTibpbJZNG7J64MIAQGg-gxt_Gmr5dmUqnyrrxd4Ti9K0hVpSypqstV12E4fdG25cHGW9x_7TUAjGpYsBqc-bhJ7DXw4qYQMZdf756X3U_aHi4el2kzlAO1Acos63FwNufs0j9DoIrRgOT6tFeYsHlVoSX3FWb7i-g-8rr2jlQCW5-1Ql4JGXLoDC4vod7DOyeOwbw92xTmJi75S2XHfRy2j43H8gjXECUS482RBKQeeGJ5FVsdQs9bAtNiyJqM4sSHBBkVFcgIN3Umv3MOUmVVYKy6USzLBj1C5WBZwgDIxxamlOgSoumc7SzLgoI2eg_FIQnaKuH6z5e62NMf8ep7M_rp-jPT8fvh5DkwvU3pQVXKJd87FZrMurMKNfRMGh0w
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1JSwMxGA1aBT3VpeJuDl5jO1-SZsabdLHFWgpWKHgoSeYbKNSpdNG_bzIzrV48eBmGWRhImOR9y3uPkFsjVZSA19hPwDChQsuMxZgpqwC0klLrTMS1p_r9cDSKBgVZPePCIGLWfIZ3_jSr5cczu_KpsmrgPbEAwm2yI4WAIKdrbRbeukPvBTsuqEXVbuOlJSUXykWB4DMnWdfhLw-VbAtpl__58QNS-SHj0cFmmzkkW5gekfLajYEWP-cxeWtmzRgOUevJ_J42V3rKfM1Zv9P8Dn1ceU0rByvZw5eeI2178QJMY5q_Q31OlvZ8a7g75mlM6r3SposKeW23ho0OK6wTmHYBypIBoEmsqNdiHSjDQw_cAsvrNTBRjApdWGS1kOgAnjLGPQzChjpWMhZKS275CSmlsxRPCUXOBcSQAIIWipsojKyLMxKO2i8GtTNS8YM1_sjVMcbrcTr_4_oN2esMn3vjXrf_dEH2_dz46gzUL0lpOV_hFdm1n8vJYn6dze433umlGg
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+%2F+International+Conference+on+Software+Engineering&rft.atitle=DesignRepair%3A+Dual-Stream+Design+Guideline-Aware+Frontend+Repair+with+Large+Language+Models&rft.au=Yuan%2C+Mingyue&rft.au=Chen%2C+Jieshan&rft.au=Xing%2C+Zhenchang&rft.au=Quigley%2C+Aaron&rft.date=2025-04-26&rft.pub=IEEE&rft.eissn=1558-1225&rft.spage=2483&rft.epage=2494&rft_id=info:doi/10.1109%2FICSE55347.2025.00109&rft.externalDocID=11030228