The use of large language models for program repair

<p>Large Language Models (LLMs) have emerged as a promising approach for automated program repair, offering code comprehension and generation capabilities that can address software bugs. Several program repair models based on LLMs have been developed recently. However, findings and insights fr...

Full description

Saved in:
Bibliographic Details
Main Author: Fida Zubair (20482610) (author)
Other Authors: Maryam Al-Hitmi (20482613) (author), Cagatay Catal (6897842) (author)
Published: 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1864513552691232768
author Fida Zubair (20482610)
author2 Maryam Al-Hitmi (20482613)
Cagatay Catal (6897842)
author2_role author
author
author_facet Fida Zubair (20482610)
Maryam Al-Hitmi (20482613)
Cagatay Catal (6897842)
author_role author
dc.creator.none.fl_str_mv Fida Zubair (20482610)
Maryam Al-Hitmi (20482613)
Cagatay Catal (6897842)
dc.date.none.fl_str_mv 2024-11-28T18:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.csi.2024.103951
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/The_use_of_large_language_models_for_program_repair/28105223
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Information and computing sciences
Artificial intelligence
Software engineering
Large language model
Program repair
Software engineering
Automated program repair
dc.title.none.fl_str_mv The use of large language models for program repair
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p>Large Language Models (LLMs) have emerged as a promising approach for automated program repair, offering code comprehension and generation capabilities that can address software bugs. Several program repair models based on LLMs have been developed recently. However, findings and insights from these efforts are scattered across various studies, lacking a systematic overview of LLMs' utilization in program repair. Therefore, this Systematic Literature Review (SLR) was conducted to investigate the current landscape of LLM utilization in program repair. This study defined seven research questions and thoroughly selected 41 relevant studies from scientific databases to explore these questions. The results showed the diverse capabilities of LLMs for program repair. The findings revealed that Encoder-Decoder architectures emerged as the most common LLM design for program repair tasks and that mostly open-access datasets were used. Several evaluation metrics were applied, primarily consisting of accuracy, exact match, and BLEU scores. Additionally, the review investigated several LLM fine-tuning methods, including fine-tuning on specialized datasets, curriculum learning, iterative approaches, and knowledge-intensified techniques. These findings pave the way for further research on utilizing the full potential of LLMs to revolutionize automated program repair.</p><h2>Other Information</h2> <p> Published in: Computer Standards & Interfaces<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.csi.2024.103951" target="_blank">https://dx.doi.org/10.1016/j.csi.2024.103951</a></p>
eu_rights_str_mv openAccess
id Manara2_cc9751dae570a6f8c3825dd7bf152af5
identifier_str_mv 10.1016/j.csi.2024.103951
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/28105223
publishDate 2024
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling The use of large language models for program repairFida Zubair (20482610)Maryam Al-Hitmi (20482613)Cagatay Catal (6897842)Information and computing sciencesArtificial intelligenceSoftware engineeringLarge language modelProgram repairSoftware engineeringAutomated program repair<p>Large Language Models (LLMs) have emerged as a promising approach for automated program repair, offering code comprehension and generation capabilities that can address software bugs. Several program repair models based on LLMs have been developed recently. However, findings and insights from these efforts are scattered across various studies, lacking a systematic overview of LLMs' utilization in program repair. Therefore, this Systematic Literature Review (SLR) was conducted to investigate the current landscape of LLM utilization in program repair. This study defined seven research questions and thoroughly selected 41 relevant studies from scientific databases to explore these questions. The results showed the diverse capabilities of LLMs for program repair. The findings revealed that Encoder-Decoder architectures emerged as the most common LLM design for program repair tasks and that mostly open-access datasets were used. Several evaluation metrics were applied, primarily consisting of accuracy, exact match, and BLEU scores. Additionally, the review investigated several LLM fine-tuning methods, including fine-tuning on specialized datasets, curriculum learning, iterative approaches, and knowledge-intensified techniques. These findings pave the way for further research on utilizing the full potential of LLMs to revolutionize automated program repair.</p><h2>Other Information</h2> <p> Published in: Computer Standards & Interfaces<br> License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.csi.2024.103951" target="_blank">https://dx.doi.org/10.1016/j.csi.2024.103951</a></p>2024-11-28T18:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.csi.2024.103951https://figshare.com/articles/journal_contribution/The_use_of_large_language_models_for_program_repair/28105223CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/281052232024-11-28T18:00:00Z
spellingShingle The use of large language models for program repair
Fida Zubair (20482610)
Information and computing sciences
Artificial intelligence
Software engineering
Large language model
Program repair
Software engineering
Automated program repair
status_str publishedVersion
title The use of large language models for program repair
title_full The use of large language models for program repair
title_fullStr The use of large language models for program repair
title_full_unstemmed The use of large language models for program repair
title_short The use of large language models for program repair
title_sort The use of large language models for program repair
topic Information and computing sciences
Artificial intelligence
Software engineering
Large language model
Program repair
Software engineering
Automated program repair