Please use this identifier to cite or link to this item:
http://hdl.handle.net/1893/35483
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Brownlee, Alexander | en_UK |
dc.contributor.author | Callan, James | en_UK |
dc.contributor.author | Even-Mendoza, Karine | en_UK |
dc.contributor.author | Geiger, Alina | en_UK |
dc.contributor.author | Hanna, Carol | en_UK |
dc.contributor.author | Petke, Justyna | en_UK |
dc.contributor.author | Sarro, Federica | en_UK |
dc.contributor.author | Sobania, Dominik | en_UK |
dc.contributor.editor | Arcaini, Paolo | en_UK |
dc.contributor.editor | Yue, Tao | en_UK |
dc.contributor.editor | Fredericks, Erik M | en_UK |
dc.date.accessioned | 2023-10-24T00:00:31Z | - |
dc.date.available | 2023-10-24T00:00:31Z | - |
dc.date.issued | 2023-12-28 | en_UK |
dc.identifier.uri | http://hdl.handle.net/1893/35483 | - |
dc.description.abstract | Large 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.iso | en | en_UK |
dc.publisher | Springer | en_UK |
dc.relation | Brownlee 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/9783031487958 | en_UK |
dc.relation.ispartofseries | Lecture Notes in Computer Science | en_UK |
dc.rights.uri | http://www.rioxx.net/licenses/under-embargo-all-rights-reserved | en_UK |
dc.title | Enhancing Genetic Improvement Mutations Using Large Language Models | en_UK |
dc.type | Part of book or chapter of book | en_UK |
dc.rights.embargodate | 2999-12-31 | en_UK |
dc.citation.issn | 0302-9743 | en_UK |
dc.type.status | AM - Accepted Manuscript | en_UK |
dc.contributor.funder | Engineering and Physical Sciences Research Council | en_UK |
dc.contributor.funder | European Commission (Horizon 2020) | en_UK |
dc.identifier.url | https://link.springer.com/book/9783031487958 | en_UK |
dc.author.email | alexander.brownlee@stir.ac.uk | en_UK |
dc.citation.btitle | Search-Based Software Engineering: 15th International Symposium, SSBSE 2023, San Francisco, CA, USA, December 8, 2023, Proceedings | en_UK |
dc.citation.date | 28/12/2023 | en_UK |
dc.citation.isbn | 9783031487958 | en_UK |
dc.citation.isbn | 9783031487965 | en_UK |
dc.publisher.address | Cham, Switzerland | en_UK |
dc.contributor.affiliation | Computing Science and Mathematics - Division | en_UK |
dc.contributor.affiliation | University College London | en_UK |
dc.contributor.affiliation | King's College London | en_UK |
dc.contributor.affiliation | Johannes Gutenberg University of Mainz | en_UK |
dc.contributor.affiliation | University College London | en_UK |
dc.contributor.affiliation | University College London | en_UK |
dc.contributor.affiliation | University College London | en_UK |
dc.contributor.affiliation | Johannes Gutenberg University of Mainz | en_UK |
dc.identifier.wtid | 1946153 | en_UK |
dc.contributor.orcid | 0000-0003-2892-5059 | en_UK |
dcterms.dateAccepted | 2023-12-28 | en_UK |
dc.date.filedepositdate | 2023-10-17 | en_UK |
rioxxterms.apc | not required | en_UK |
rioxxterms.type | Book chapter | en_UK |
rioxxterms.version | AM | en_UK |
local.rioxx.author | Brownlee, Alexander|0000-0003-2892-5059 | en_UK |
local.rioxx.author | Callan, James| | en_UK |
local.rioxx.author | Even-Mendoza, Karine| | en_UK |
local.rioxx.author | Geiger, Alina| | en_UK |
local.rioxx.author | Hanna, Carol| | en_UK |
local.rioxx.author | Petke, Justyna| | en_UK |
local.rioxx.author | Sarro, Federica| | en_UK |
local.rioxx.author | Sobania, Dominik| | en_UK |
local.rioxx.project | Project ID unknown|Engineering and Physical Sciences Research Council|http://dx.doi.org/10.13039/501100000266 | en_UK |
local.rioxx.project | Project ID unknown|European Commission (Horizon 2020)| | en_UK |
local.rioxx.contributor | Arcaini, Paolo| | en_UK |
local.rioxx.contributor | Yue, Tao| | en_UK |
local.rioxx.contributor | Fredericks, Erik M| | en_UK |
local.rioxx.freetoreaddate | 2273-11-29 | en_UK |
local.rioxx.licence | http://www.rioxx.net/licenses/under-embargo-all-rights-reserved|| | en_UK |
local.rioxx.filename | ssbse23challenge-final31.pdf | en_UK |
local.rioxx.filecount | 1 | en_UK |
local.rioxx.source | 9783031487965 | en_UK |
Appears in Collections: | Computing Science and Mathematics Book Chapters and Sections |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
ssbse23challenge-final31.pdf | Fulltext - Accepted Version | 203.09 kB | Adobe PDF | Under 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.