Towards LLM-Powered Consistency in Model-Based Low-Code Platforms

Low-code platforms often use various models that define the application built by citizen developers. With the increasing size and complexity of the applications built using low-code platforms, the number of required models and the dependencies between them expand. However, with increased complexity,...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:International Conference on Software Architecture Companion (Online) s. 364 - 369
Hlavní autoři: Hagel, Nathan, Hili, Nicolas, Bartel, Alexander, Koziolek, Anne
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 31.03.2025
Témata:
ISSN:2768-4288
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Low-code platforms often use various models that define the application built by citizen developers. With the increasing size and complexity of the applications built using low-code platforms, the number of required models and the dependencies between them expand. However, with increased complexity, keeping these models consistent during the development or evolution of the application is crucial and often a non-trivial task for citizen developers. In this paper, we present four approaches to how LLMs can be used and integrated on the architecture level into low-code platforms to (i) create consistent models automatically, (ii) keep models consistent based on different types of dependencies, and (iii) support users in maintaining consistent models during the development. We implemented the approaches in a prototype and evaluated them in an exploratory study. The results show that state-of-the-art LLMs are capable of preserving consistency for low-code models as well as generating correct and consistent models in various scenarios.
AbstractList Low-code platforms often use various models that define the application built by citizen developers. With the increasing size and complexity of the applications built using low-code platforms, the number of required models and the dependencies between them expand. However, with increased complexity, keeping these models consistent during the development or evolution of the application is crucial and often a non-trivial task for citizen developers. In this paper, we present four approaches to how LLMs can be used and integrated on the architecture level into low-code platforms to (i) create consistent models automatically, (ii) keep models consistent based on different types of dependencies, and (iii) support users in maintaining consistent models during the development. We implemented the approaches in a prototype and evaluated them in an exploratory study. The results show that state-of-the-art LLMs are capable of preserving consistency for low-code models as well as generating correct and consistent models in various scenarios.
Author Hili, Nicolas
Koziolek, Anne
Bartel, Alexander
Hagel, Nathan
Author_xml – sequence: 1
  givenname: Nathan
  surname: Hagel
  fullname: Hagel, Nathan
  email: nathan.hagel@kit.edu
  organization: KASTEL, Karlsruhe Institute of Technology,Karlsruhe,Germany
– sequence: 2
  givenname: Nicolas
  surname: Hili
  fullname: Hili, Nicolas
  email: nicolas.hili@univ-grenoble-alpes.fr
  organization: Univ. Grenoble Alpes, CNRS Grenoble INP, LIG,Grenoble,France,38000
– sequence: 3
  givenname: Alexander
  surname: Bartel
  fullname: Bartel, Alexander
  email: alexander.bartel@hnu.de
  organization: Neu-Ulm University of Applied Sciences,Dep. Information Management,Neu-Ulm,Germany
– sequence: 4
  givenname: Anne
  surname: Koziolek
  fullname: Koziolek, Anne
  email: anne.koziolek@kit.edu
  organization: KASTEL, Karlsruhe Institute of Technology,Karlsruhe,Germany
BookMark eNotkN1Kw0AUhFdRsNa8gUheYGM2Z3_OXsZgtZBiwXpdNtkTiKRZyQZK396AXg0z3zAXc89uxjASY08iz4TI7fO2-ix5pZVQkBV5obI8zxVescQaiwBLDKD1NVsVRiOXBeIdS2L8Xmog0CKKFSsP4ewmH9O63vF9ONNEPq3CGPs409he0n5Md8HTwF9cXFAdzrxafLof3NyF6RQf2G3nhkjJv67Z1-b1UL3z-uNtW5U174XBmUOjZKcQfSOldKCNNAW2phOtJbKy8apRSoMkZUB75ayW2FrwVgtHyltYs8e_3Z6Ijj9Tf3LT5bgcIaQFC7-I2kw5
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICSA-C65153.2025.00058
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
EISBN 9798331533366
EISSN 2768-4288
EndPage 369
ExternalDocumentID 11014939
Genre orig-research
GrantInformation_xml – fundername: Deutsche Forschungsgemeinschaft
  grantid: 1608-501798263
  funderid: 10.13039/501100001659
GroupedDBID 6IE
6IF
6IL
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
OCL
RIE
RIL
ID FETCH-LOGICAL-i178t-3b54f588db444a3674728c7f1c9ee94bd5b55634e5736d5a9648c93d961ae5d93
IEDL.DBID RIE
ISICitedReferencesCount 1
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001549223000051&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
IngestDate Wed Jun 04 06:02:10 EDT 2025
IsPeerReviewed false
IsScholarly false
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i178t-3b54f588db444a3674728c7f1c9ee94bd5b55634e5736d5a9648c93d961ae5d93
PageCount 6
ParticipantIDs ieee_primary_11014939
PublicationCentury 2000
PublicationDate 2025-March-31
PublicationDateYYYYMMDD 2025-03-31
PublicationDate_xml – month: 03
  year: 2025
  text: 2025-March-31
  day: 31
PublicationDecade 2020
PublicationTitle International Conference on Software Architecture Companion (Online)
PublicationTitleAbbrev ICSA-C
PublicationYear 2025
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0003189881
Score 1.9119607
Snippet Low-code platforms often use various models that define the application built by citizen developers. With the increasing size and complexity of the...
SourceID ieee
SourceType Publisher
StartPage 364
SubjectTerms Artificial intelligence
Complexity theory
Computer architecture
consistency
DSL
LLM
low-code development platform
meta-model
Model driven engineering
Prototypes
Software architecture
Title Towards LLM-Powered Consistency in Model-Based Low-Code Platforms
URI https://ieeexplore.ieee.org/document/11014939
WOSCitedRecordID wos001549223000051&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/eLvHCXMwlV3LSgMxFA22uHClYsU3WbiNnUwyeSzrYFEYy4AVuivJ5A4UylTaqeLfm6S1unHhLskm3Dy4j-Scg9BtIpyQJqVEplb5BAUMsU46QqUT_p4HXtxImV_I0UhNJrrcgtUjFgYA4uczuAvN-JbvFtU6lMr6NAjLaqY7qCOl3IC1dgUVfzi1UnSLAqaJ7j_lLwOSB61v5hPBNBRPkiDt_ktGJXqR4eE_5z9CvR88Hi53nuYY7UFzggbj-ON1hYvimZRB7AwcjvqbqxAHf-JZg4PS2Zzce0_lcLH4ILnv43Ju2hCqrnrodfgwzh_JVhCBzKhULWE243WmlLOcc8OETwVSVcmaVhpAc-syG_i-OGSSCZcZLbiqNHNaUAOZ0-wUdZtFA2cI14bLhNccmAQfUTlrrK1kQl0tKh-j1OeoF-yfvm04L6bfpl_8MX6JDsISb9B6V6jbLtdwjfar93a2Wt7EnfoC9bCTWg
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3LS8MwHA46BT2pOPFtDl7jmibN4ziLY8NuFJyw20iaFAajk7VT_O9Nsjm9ePCW5JRfHvweyfd9ANxHzDCuYox4rIVLUKxC2nCDMDfM3XPPixso8zM-GonJROYbsHrAwlhrw-cz--Cb4S3fLIqVL5V1sBeWlUTugr2E0hiv4Vrbkoo7nlIIvMEB40h2BulLF6Ve7Zu4VDD25ZPIi7v_ElIJfqR39M8ZHIP2DyIP5ltfcwJ2bHUKuuPw57WGWTZEuZc7swYGBc7aR8KfcFZBr3U2R4_OVxmYLT5Q6vown6vGB6t1G7z2nsZpH20kEdAMc9EgohNaJkIYTSlVhLlkIBYFL3EhrZVUm0R7xi9qE06YSZRkVBSSGMmwsomR5Ay0qkVlzwEsFeURLakl3LqYymildcEjbEpWuCilvABtb__0bc16Mf02_fKP8Ttw0B8Ps2k2GD1fgUO_3Gvs3jVoNcuVvQH7xXszq5e3Yde-ANOMlqE
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=International+Conference+on+Software+Architecture+Companion+%28Online%29&rft.atitle=Towards+LLM-Powered+Consistency+in+Model-Based+Low-Code+Platforms&rft.au=Hagel%2C+Nathan&rft.au=Hili%2C+Nicolas&rft.au=Bartel%2C+Alexander&rft.au=Koziolek%2C+Anne&rft.date=2025-03-31&rft.pub=IEEE&rft.eissn=2768-4288&rft.spage=364&rft.epage=369&rft_id=info:doi/10.1109%2FICSA-C65153.2025.00058&rft.externalDocID=11014939