Please use this identifier to cite or link to this item: http://hdl.handle.net/1893/35483
Full metadata record
DC FieldValueLanguage
dc.contributor.authorBrownlee, Alexanderen_UK
dc.contributor.authorCallan, Jamesen_UK
dc.contributor.authorEven-Mendoza, Karineen_UK
dc.contributor.authorGeiger, Alinaen_UK
dc.contributor.authorHanna, Carolen_UK
dc.contributor.authorPetke, Justynaen_UK
dc.contributor.authorSarro, Federicaen_UK
dc.contributor.authorSobania, Dominiken_UK
dc.contributor.editorArcaini, Paoloen_UK
dc.contributor.editorYue, Taoen_UK
dc.contributor.editorFredericks, Erik Men_UK
dc.date.accessioned2023-10-24T00:00:31Z-
dc.date.available2023-10-24T00:00:31Z-
dc.date.issued2023-12-28en_UK
dc.identifier.urihttp://hdl.handle.net/1893/35483-
dc.description.abstractLarge language models (LLMs) have been successfully applied to software engineering tasks, including program repair. However, their application in search-based techniques such as Genetic Improvement (GI) is still largely unexplored. In this paper, we evaluate the use of LLMs as mutation operators for GI to improve the search process. We expand the Gin Java GI toolkit to call OpenAI's API to generate edits for the JCodec tool. We randomly sample the space of edits using 5 different edit types. We find that the number of patches passing unit tests is up to 75% higher with LLM-based edits than with standard Insert edits. Further, we observe that the patches found with LLMs are generally less diverse compared to standard edits. We ran GI with local search to find runtime improvements. Although many improving patches are found by LLM-enhanced GI, the best improving patch was found by standard GI.en_UK
dc.language.isoenen_UK
dc.publisherSpringeren_UK
dc.relationBrownlee A, Callan J, Even-Mendoza K, Geiger A, Hanna C, Petke J, Sarro F & Sobania D (2023) Enhancing Genetic Improvement Mutations Using Large Language Models. In: Arcaini P, Yue T & Fredericks EM (eds.) <i>Search-Based Software Engineering: 15th International Symposium, SSBSE 2023, San Francisco, CA, USA, December 8, 2023, Proceedings</i>. Lecture Notes in Computer Science. Cham, Switzerland: Springer. https://link.springer.com/book/9783031487958en_UK
dc.relation.ispartofseriesLecture Notes in Computer Scienceen_UK
dc.rights.urihttp://www.rioxx.net/licenses/under-embargo-all-rights-reserveden_UK
dc.titleEnhancing Genetic Improvement Mutations Using Large Language Modelsen_UK
dc.typePart of book or chapter of booken_UK
dc.rights.embargodate2999-12-31en_UK
dc.citation.issn0302-9743en_UK
dc.type.statusAM - Accepted Manuscripten_UK
dc.contributor.funderEngineering and Physical Sciences Research Councilen_UK
dc.contributor.funderEuropean Commission (Horizon 2020)en_UK
dc.identifier.urlhttps://link.springer.com/book/9783031487958en_UK
dc.author.emailalexander.brownlee@stir.ac.uken_UK
dc.citation.btitleSearch-Based Software Engineering: 15th International Symposium, SSBSE 2023, San Francisco, CA, USA, December 8, 2023, Proceedingsen_UK
dc.citation.date28/12/2023en_UK
dc.citation.isbn9783031487958en_UK
dc.citation.isbn9783031487965en_UK
dc.publisher.addressCham, Switzerlanden_UK
dc.contributor.affiliationComputing Science and Mathematics - Divisionen_UK
dc.contributor.affiliationUniversity College Londonen_UK
dc.contributor.affiliationKing's College Londonen_UK
dc.contributor.affiliationJohannes Gutenberg University of Mainzen_UK
dc.contributor.affiliationUniversity College Londonen_UK
dc.contributor.affiliationUniversity College Londonen_UK
dc.contributor.affiliationUniversity College Londonen_UK
dc.contributor.affiliationJohannes Gutenberg University of Mainzen_UK
dc.identifier.wtid1946153en_UK
dc.contributor.orcid0000-0003-2892-5059en_UK
dcterms.dateAccepted2023-12-28en_UK
dc.date.filedepositdate2023-10-17en_UK
rioxxterms.apcnot requireden_UK
rioxxterms.typeBook chapteren_UK
rioxxterms.versionAMen_UK
local.rioxx.authorBrownlee, Alexander|0000-0003-2892-5059en_UK
local.rioxx.authorCallan, James|en_UK
local.rioxx.authorEven-Mendoza, Karine|en_UK
local.rioxx.authorGeiger, Alina|en_UK
local.rioxx.authorHanna, Carol|en_UK
local.rioxx.authorPetke, Justyna|en_UK
local.rioxx.authorSarro, Federica|en_UK
local.rioxx.authorSobania, Dominik|en_UK
local.rioxx.projectProject ID unknown|Engineering and Physical Sciences Research Council|http://dx.doi.org/10.13039/501100000266en_UK
local.rioxx.projectProject ID unknown|European Commission (Horizon 2020)|en_UK
local.rioxx.contributorArcaini, Paolo|en_UK
local.rioxx.contributorYue, Tao|en_UK
local.rioxx.contributorFredericks, Erik M|en_UK
local.rioxx.freetoreaddate2273-11-29en_UK
local.rioxx.licencehttp://www.rioxx.net/licenses/under-embargo-all-rights-reserved||en_UK
local.rioxx.filenamessbse23challenge-final31.pdfen_UK
local.rioxx.filecount1en_UK
local.rioxx.source9783031487965en_UK
Appears in Collections:Computing Science and Mathematics Book Chapters and Sections

Files in This Item:
File Description SizeFormat 
ssbse23challenge-final31.pdfFulltext - Accepted Version203.09 kBAdobe PDFUnder Permanent Embargo    Request a copy


This item is protected by original copyright



Items in the Repository are protected by copyright, with all rights reserved, unless otherwise indicated.

The metadata of the records in the Repository are available under the CC0 public domain dedication: No Rights Reserved https://creativecommons.org/publicdomain/zero/1.0/

If you believe that any material held in STORRE infringes copyright, please contact library@stir.ac.uk providing details and we will remove the Work from public display in STORRE and investigate your claim.