{"id":"https://openalex.org/W4415583980","doi":"https://doi.org/10.1145/3755881.3755901","title":"CodeCleaner: Mitigating Data Contamination for LLM Benchmarking","display_name":"CodeCleaner: Mitigating Data Contamination for LLM Benchmarking","publication_year":2025,"publication_date":"2025-06-20","ids":{"openalex":"https://openalex.org/W4415583980","doi":"https://doi.org/10.1145/3755881.3755901"},"language":"en","primary_location":{"id":"doi:10.1145/3755881.3755901","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3755881.3755901","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3755881.3755901","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Internetware","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3755881.3755901","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053372458","display_name":"Jialun Cao","orcid":"https://orcid.org/0000-0003-4892-6294"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jialun Cao","raw_affiliation_strings":["Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-4892-6294","affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077331062","display_name":"Songqiang Chen","orcid":"https://orcid.org/0000-0002-1220-8728"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Songqiang Chen","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-1220-8728","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077307201","display_name":"Wuqi Zhang","orcid":"https://orcid.org/0000-0001-8039-0528"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wuqi Zhang","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0001-8039-0528","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114730187","display_name":"Hau Ching Lo","orcid":"https://orcid.org/0009-0000-4919-6292"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hau Ching Lo","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0000-4919-6292","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037974123","display_name":"Yeting Li","orcid":"https://orcid.org/0000-0003-0991-4231"},"institutions":[{"id":"https://openalex.org/I4210137199","display_name":"Aerospace Information Research Institute","ror":"https://ror.org/0419fj215","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210137199"]},{"id":"https://openalex.org/I4210156404","display_name":"Institute of Information Engineering","ror":"https://ror.org/04r53se39","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210156404"]},{"id":"https://openalex.org/I4210159876","display_name":"Institute of Physics","ror":"https://ror.org/05cvf7v30","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210159876"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yeting Li","raw_affiliation_strings":["Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-0991-4231","affiliations":[{"raw_affiliation_string":"Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China and University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210137199","https://openalex.org/I4210156404","https://openalex.org/I4210159876"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034057959","display_name":"Shing-Chi Cheung","orcid":"https://orcid.org/0000-0002-3508-7172"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Shing-Chi Cheung","raw_affiliation_strings":["The Hong Kong University of Science and Technology, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-3508-7172","affiliations":[{"raw_affiliation_string":"The Hong Kong University of Science and Technology, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.37009658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"71","last_page":"83"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12034","display_name":"Digital and Cyber Forensics","score":0.9828000068664551,"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"}},{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9710999727249146,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/code-refactoring","display_name":"Code refactoring","score":0.8151999711990356},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.4878999888896942},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.44209998846054077},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.4242999851703644},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.41690000891685486},{"id":"https://openalex.org/keywords/credibility","display_name":"Credibility","score":0.41620001196861267},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.38429999351501465},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.3587999939918518},{"id":"https://openalex.org/keywords/unavailability","display_name":"Unavailability","score":0.3361999988555908}],"concepts":[{"id":"https://openalex.org/C152752567","wikidata":"https://www.wikidata.org/wiki/Q116877","display_name":"Code refactoring","level":3,"score":0.8151999711990356},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.628600001335144},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.49300000071525574},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.41690000891685486},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.41620001196861267},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.38429999351501465},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3587999939918518},{"id":"https://openalex.org/C2780505938","wikidata":"https://www.wikidata.org/wiki/Q17093282","display_name":"Unavailability","level":2,"score":0.3361999988555908},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33059999346733093},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C104054115","wikidata":"https://www.wikidata.org/wiki/Q216828","display_name":"Cohesion (chemistry)","level":2,"score":0.3043000102043152},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.2992999851703644},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.29910001158714294},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.28029999136924744},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C199519371","wikidata":"https://www.wikidata.org/wiki/Q942695","display_name":"Source lines of code","level":3,"score":0.26600000262260437},{"id":"https://openalex.org/C192465680","wikidata":"https://www.wikidata.org/wiki/Q1413450","display_name":"Precondition","level":2,"score":0.2651999890804291},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.25270000100135803},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3755881.3755901","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3755881.3755901","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3755881.3755901","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Internetware","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-167572","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-167572","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3755881.3755901","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3755881.3755901","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3755881.3755901","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Conference on Internetware","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4415583980.pdf","grobid_xml":"https://content.openalex.org/works/W4415583980.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W2058373514","https://openalex.org/W2143861926","https://openalex.org/W2795435272","https://openalex.org/W2950368691","https://openalex.org/W3090988182","https://openalex.org/W3109744225","https://openalex.org/W3172642864","https://openalex.org/W3194983542","https://openalex.org/W3213241618","https://openalex.org/W4210497109","https://openalex.org/W4249744258","https://openalex.org/W4298289021","https://openalex.org/W4378591002","https://openalex.org/W4378942602","https://openalex.org/W4384345708","https://openalex.org/W4385565597","https://openalex.org/W4385965989","https://openalex.org/W4389518953","https://openalex.org/W4390442456","https://openalex.org/W4391579642","https://openalex.org/W4392402185","https://openalex.org/W4393407110","https://openalex.org/W4400190921","https://openalex.org/W4402670101","https://openalex.org/W4403536427","https://openalex.org/W4403536900","https://openalex.org/W4404780897","https://openalex.org/W4411272397"],"related_works":[],"abstract_inverted_index":{"Data":[0],"contamination":[1,137],"presents":[2,84],"a":[3,55],"critical":[4],"barrier":[5],"preventing":[6],"widespread":[7,76],"industrial":[8,77],"adoption":[9],"of":[10,41,64,93,161,196],"advanced":[11],"software":[12],"engineering":[13],"techniques":[14,73],"that":[15],"leverage":[16],"large":[17],"language":[18],"models":[19],"(LLMs).This":[20],"phenomenon":[21],"occurs":[22],"when":[23,167],"evaluation":[24],"data":[25,60,136,178,219],"inadvertently":[26],"overlaps":[27],"with":[28],"the":[29,39,62,80,85,91,126,154],"public":[30],"code":[31,47,66,94],"repositories":[32],"used":[33],"to":[34,58,89,134,152,184,189,212],"train":[35],"LLMs,":[36],"severely":[37],"undermining":[38],"credibility":[40],"performance":[42,201],"evaluations.Code":[43],"refactoring,":[44],"which":[45],"comprises":[46],"restructuring":[48],"and":[49,69,102,105,120,138,147],"variable":[50],"renaming,":[51],"has":[52,74],"emerged":[53],"as":[54],"promising":[56],"measure":[57],"mitigate":[59],"contamination.However,":[61],"lack":[63],"automated":[65],"refactoring":[67,72,95],"tools":[68],"scientifically":[70],"validated":[71],"hampered":[75],"implementation.To":[78],"bridge":[79],"gap,":[81],"this":[82],"paper":[83],"first":[86],"systematic":[87],"study":[88],"examine":[90],"efficacy":[92,155],"operators":[96,114,131,157,170,183],"at":[97,210],"multiple":[98,118],"scales":[99,119],"(method-level,":[100],"class-level,":[101],"crossclass":[103],"level)":[104],"in":[106,117,171,176,199],"different":[107],"programming":[108],"languages.We":[109],"develop":[110],"CodeCleaner,":[111,172],"including":[112],"11":[113],"for":[115,122,128],"Python":[116],"4":[121],"Java.We":[123],"elaborate":[124],"on":[125,216],"rationale":[127],"why":[129],"these":[130],"could":[132],"work":[133],"resolve":[135],"use":[139],"both":[140],"data-wise":[141],"(e.g.,":[142,150],"N-gram":[143],"matching":[144],"overlap":[145,163],"ratio)":[146],"model-wise":[148],"metrics":[149],"perplexity)":[151],"quantify":[153],"after":[156,202],"are":[158],"applied.A":[159],"drop":[160],"75%":[162],"ratio":[164],"is":[165],"found":[166],"applying":[168,203],"all":[169],"demonstrating":[173],"their":[174,187],"effectiveness":[175],"addressing":[177],"contamination.Besides,":[179],"we":[180],"migrate":[181],"four":[182],"Java,":[185],"showing":[186],"generalizability":[188],"another":[190],"language.We":[191],"also":[192],"observed":[193],"an":[194],"average":[195],"19%":[197],"decrease":[198],"LLMs'":[200],"our":[204],"operators.We":[205],"make":[206],"CodeCleaner":[207],"online":[208],"available":[209],"https://github.com/ArabelaTso/CodeCleaner-v1":[211],"facilitate":[213],"further":[214],"studies":[215],"mitigating":[217],"LLM":[218],"contamination.":[220]},"counts_by_year":[],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-28T00:00:00"}
