{"id":"https://openalex.org/W4412888305","doi":"https://doi.org/10.18653/v1/2025.findings-acl.550","title":"CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings","display_name":"CoDet-M4: Detecting Machine-Generated Code in Multi-Lingual, Multi-Generator and Multi-Domain Settings","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412888305","doi":"https://doi.org/10.18653/v1/2025.findings-acl.550"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.findings-acl.550","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.550","pdf_url":"https://aclanthology.org/2025.findings-acl.550.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-acl.550.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000211688","display_name":"Daniil Orel","orcid":"https://orcid.org/0009-0007-5600-7032"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I91044093","display_name":"Zayed University","ror":"https://ror.org/03snqfa66","country_code":"AE","type":"education","lineage":["https://openalex.org/I91044093"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Daniil Orel","raw_affiliation_strings":["Zayed University of Artificial Intelligence , UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zayed University of Artificial Intelligence , UAE","institution_ids":["https://openalex.org/I4210113480","https://openalex.org/I91044093"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033886004","display_name":"Dilshod Azizov","orcid":"https://orcid.org/0000-0002-0572-8813"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I91044093","display_name":"Zayed University","ror":"https://ror.org/03snqfa66","country_code":"AE","type":"education","lineage":["https://openalex.org/I91044093"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Dilshod Azizov","raw_affiliation_strings":["Zayed University of Artificial Intelligence , UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zayed University of Artificial Intelligence , UAE","institution_ids":["https://openalex.org/I4210113480","https://openalex.org/I91044093"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012055259","display_name":"Preslav Nakov","orcid":"https://orcid.org/0000-0002-3600-1510"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]},{"id":"https://openalex.org/I91044093","display_name":"Zayed University","ror":"https://ror.org/03snqfa66","country_code":"AE","type":"education","lineage":["https://openalex.org/I91044093"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Preslav Nakov","raw_affiliation_strings":["Zayed University of Artificial Intelligence , UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zayed University of Artificial Intelligence , UAE","institution_ids":["https://openalex.org/I4210113480","https://openalex.org/I91044093"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.21547642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10570","last_page":"10593"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9009000062942505,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9009000062942505,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8000601530075073},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.6389608979225159},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.5579342246055603},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5471415519714355},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5374959111213684},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3966580033302307},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.17555227875709534},{"id":"https://openalex.org/keywords/power","display_name":"Power (physics)","score":0.06345072388648987},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06332463026046753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8000601530075073},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.6389608979225159},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5579342246055603},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5471415519714355},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5374959111213684},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3966580033302307},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.17555227875709534},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.06345072388648987},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06332463026046753},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-acl.550","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.550","pdf_url":"https://aclanthology.org/2025.findings-acl.550.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-acl.550","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-acl.550","pdf_url":"https://aclanthology.org/2025.findings-acl.550.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412888305.pdf","grobid_xml":"https://content.openalex.org/works/W4412888305.grobid-xml"},"referenced_works_count":1,"referenced_works":["https://openalex.org/W4323570365"],"related_works":["https://openalex.org/W1480878783","https://openalex.org/W4287064674","https://openalex.org/W3188573563","https://openalex.org/W3201246199","https://openalex.org/W3122369893","https://openalex.org/W2387634031","https://openalex.org/W2163672025","https://openalex.org/W2048831961","https://openalex.org/W1606349578","https://openalex.org/W4399567378"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"revolutionized":[5],"code":[6,31,82,87,100,125,142],"generation,":[7],"automating":[8],"programming":[9,19,61,85,150],"with":[10],"remarkable":[11],"efficiency.However,":[12],"this":[13,45,67],"has":[14,39],"had":[15],"important":[16],"consequences":[17],"for":[18,33,124,169],"skills,":[20],"ethics,":[21],"and":[22,36,52,54,79,89,98,110,122,137,143,149],"assessment":[23],"integrity,":[24],"thus":[25],"making":[26],"the":[27,170],"detection":[28],"of":[29,60,75,113,140],"LLM-generated":[30,80,162],"essential":[32],"maintaining":[34],"accountability":[35],"standards.While,":[37],"there":[38],"been":[40],"some":[41],"previous":[42],"research":[43],"on":[44,130],"problem,":[46],"it":[47],"generally":[48],"lacks":[49],"domain":[50],"coverage":[51],"robustness,":[53],"only":[55],"covers":[56],"a":[57,72,92,166],"small":[58],"number":[59],"languages.Here,":[62],"we":[63,70],"aim":[64],"to":[65,145],"bridge":[66],"gap.In":[68],"particular,":[69],"propose":[71],"framework":[73,157],"capable":[74],"distinguishing":[76],"between":[77],"human-written":[78,160],"program":[81,163],"across":[83],"multiple":[84],"languages,":[86],"generators,":[88,101],"domains.We":[90],"use":[91],"large-scale":[93],"dataset":[94],"from":[95,161],"renowned":[96],"platforms":[97],"LLM-based":[99],"alongside":[102],"applying":[103],"rigorous":[104],"data":[105],"quality":[106],"checks,":[107],"feature":[108],"engineering,":[109],"comparative":[111],"analysis":[112],"traditional":[114],"machine":[115],"learning":[116],"models,":[117,147],"pre-trained":[118],"language":[119],"models":[120],"(PLMs),":[121],"LLMs":[123],"detection.We":[126],"perform":[127],"an":[128],"evaluation":[129],"out-of-domain":[131],"scenarios,":[132],"such":[133],"as":[134],"detecting":[135],"authorship":[136,139],"hybrid":[138],"generated":[141],"generalizing":[144],"unseen":[146],"domains,":[148],"languages.Our":[151],"extensive":[152],"experiments":[153],"show":[154],"that":[155],"our":[156],"effectively":[158],"distinguishes":[159],"code,":[164],"setting":[165],"new":[167],"benchmark":[168],"task.":[171]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
