Publicação
Large language models in automated repair of haskell type errors
| Resumo: | This paper introduces a new method of Automated Program Repair that relies on a combination of the GPT-4 Large Language Model and automatic type checking of Haskell programs. This method identifies the source of a type error and asks GPT-4 to fix that specific portion of the program. Then, QuickCheck is used to automatically generate a large set of test cases to validate whether the generated repair behaves as the correct solution. Our publicly available experiments revealed a success rate of 88.5% in normal conditions. However, more detailed testing should be performed to more accurately evaluate this form of APR. |
|---|---|
| Autores principais: | Santos, Sofia |
| Outros Autores: | Saraiva, João; Ribeiro, Francisco |
| Assunto: | Automated program repair Large language model Fault localization Code generation Type checking Automatic testing |
| Ano: | 2024 |
| País: | Portugal |
| Tipo de documento: | comunicação em conferência |
| Tipo de acesso: | acesso aberto |
| Instituição associada: | Universidade do Minho |
| Idioma: | inglês |
| Origem: | RepositóriUM - Universidade do Minho |
| _version_ | 1867438691316662272 |
|---|---|
| author | Santos, Sofia |
| author2 | Saraiva, João Ribeiro, Francisco |
| author2_role | author author |
| author_facet | Santos, Sofia Saraiva, João Ribeiro, Francisco |
| author_role | author |
| contributor_name_str_mv | RepositóriUM - Universidade do Minho |
| country_str | PT |
| creators_json_txt | [{\"Person.name\":\"Santos, Sofia\"},{\"Person.name\":\"Saraiva, João\"},{\"Person.name\":\"Ribeiro, Francisco\"}] |
| datacite.contributors.contributor.contributorName.fl_str_mv | RepositóriUM - Universidade do Minho |
| datacite.creators.creator.creatorName.fl_str_mv | Santos, Sofia Saraiva, João Ribeiro, Francisco |
| datacite.date.Accepted.fl_str_mv | 2024-01-01T00:00:00Z |
| datacite.date.available.fl_str_mv | 2025-05-22T07:51:22Z |
| datacite.date.embargoed.fl_str_mv | 2025-05-22T07:51:22Z |
| datacite.rights.fl_str_mv | http://purl.org/coar/access_right/c_abf2 |
| datacite.subjects.subject.fl_str_mv | Automated program repair Large language model Fault localization Code generation Type checking Automatic testing |
| datacite.titles.title.fl_str_mv | Large language models in automated repair of haskell type errors |
| dc.contributor.none.fl_str_mv | RepositóriUM - Universidade do Minho |
| dc.creator.none.fl_str_mv | Santos, Sofia Saraiva, João Ribeiro, Francisco |
| dc.date.Accepted.fl_str_mv | 2024-01-01T00:00:00Z |
| dc.date.available.fl_str_mv | 2025-05-22T07:51:22Z |
| dc.date.embargoed.fl_str_mv | 2025-05-22T07:51:22Z |
| dc.format.none.fl_str_mv | application/pdf |
| dc.identifier.none.fl_str_mv | https://hdl.handle.net/1822/95655 |
| dc.language.none.fl_str_mv | eng |
| dc.publisher.none.fl_str_mv | ACM |
| dc.rights.none.fl_str_mv | http://purl.org/coar/access_right/c_abf2 |
| dc.subject.none.fl_str_mv | Automated program repair Large language model Fault localization Code generation Type checking Automatic testing |
| dc.title.fl_str_mv | Large language models in automated repair of haskell type errors |
| dc.type.none.fl_str_mv | http://purl.org/coar/resource_type/c_5794 |
| description | This paper introduces a new method of Automated Program Repair that relies on a combination of the GPT-4 Large Language Model and automatic type checking of Haskell programs. This method identifies the source of a type error and asks GPT-4 to fix that specific portion of the program. Then, QuickCheck is used to automatically generate a large set of test cases to validate whether the generated repair behaves as the correct solution. Our publicly available experiments revealed a success rate of 88.5% in normal conditions. However, more detailed testing should be performed to more accurately evaluate this form of APR. |
| dirty | 0 |
| eu_rights_str_mv | openAccess |
| format | conferencePaper |
| fulltext.url.fl_str_mv | https://repositorium.uminho.pt/bitstreams/26ffe5b6-d247-4658-ad66-7544549286bf/download |
| id | rum_5495c250c4c3e7caedbfddc7f27da88c |
| identifier.url.fl_str_mv | https://hdl.handle.net/1822/95655 |
| instacron_str | repositorium |
| institution | Universidade do Minho |
| instname_str | Universidade do Minho |
| language | eng |
| network_acronym_str | rum |
| network_name_str | RepositóriUM - Universidade do Minho |
| oai_identifier_str | oai:repositorium.uminho.pt:1822/95655 |
| organization_str_mv | urn:organizationAcronym:repositorium |
| person_str_mv | Santos, Sofia Saraiva, João Ribeiro, Francisco |
| publishDate | 2024 |
| publisher.none.fl_str_mv | ACM |
| reponame_str | RepositóriUM - Universidade do Minho |
| repository_id_str | urn:repositoryAcronym:rum |
| service_str_mv | urn:repositoryAcronym:rum |
| spelling | engACMporThis paper introduces a new method of Automated Program Repair that relies on a combination of the GPT-4 Large Language Model and automatic type checking of Haskell programs. This method identifies the source of a type error and asks GPT-4 to fix that specific portion of the program. Then, QuickCheck is used to automatically generate a large set of test cases to validate whether the generated repair behaves as the correct solution. Our publicly available experiments revealed a success rate of 88.5% in normal conditions. However, more detailed testing should be performed to more accurately evaluate this form of APR.application/pdfporLarge language models in automated repair of haskell type errorsSantos, SofiaSaraiva, JoãoRibeiro, FranciscoHostingInstitutionOrganizationalRepositóriUM - Universidade do Minhoe-mailmailto:repositorium@usdb.uminho.ptrepositorium@usdb.uminho.ptISBNIsPartOf[9798400705779]ISSNIsPartOf979-8-4007-0577-9DOIIsPartOf10.1145/3643788.36480122025-05-22T07:51:22Z20242024-01-01T00:00:00ZHandlehttps://hdl.handle.net/1822/95655http://purl.org/coar/access_right/c_abf2open accessAutomated program repairLarge language modelFault localizationCode generationType checkingAutomatic testing511501 bytesother research producthttp://purl.org/coar/resource_type/c_5794conference paperhttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://repositorium.uminho.pt/bitstreams/26ffe5b6-d247-4658-ad66-7544549286bf/download |
| spellingShingle | Large language models in automated repair of haskell type errors Santos, Sofia Automated program repair Large language model Fault localization Code generation Type checking Automatic testing |
| status | SINGLETON |
| subject.fl_str_mv | Automated program repair Large language model Fault localization Code generation Type checking Automatic testing |
| title | Large language models in automated repair of haskell type errors |
| title_full | Large language models in automated repair of haskell type errors |
| title_fullStr | Large language models in automated repair of haskell type errors |
| title_full_unstemmed | Large language models in automated repair of haskell type errors |
| title_short | Large language models in automated repair of haskell type errors |
| title_sort | Large language models in automated repair of haskell type errors |
| topic | Automated program repair Large language model Fault localization Code generation Type checking Automatic testing |
| topic_facet | Automated program repair Large language model Fault localization Code generation Type checking Automatic testing |
| url | https://hdl.handle.net/1822/95655 |
| visible | 1 |