{"id":"https://openalex.org/W7117149652","doi":"https://doi.org/10.1145/3756681.3756993","title":"Benchmarking LLM for Code Smells Detection: OpenAI GPT-4.0 vs DeepSeek-V3","display_name":"Benchmarking LLM for Code Smells Detection: OpenAI GPT-4.0 vs DeepSeek-V3","publication_year":2025,"publication_date":"2025-06-17","ids":{"openalex":"https://openalex.org/W7117149652","doi":"https://doi.org/10.1145/3756681.3756993"},"language":null,"primary_location":{"id":"doi:10.1145/3756681.3756993","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756681.3756993","pdf_url":null,"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 29th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3756681.3756993","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053558581","display_name":"Ahmed R. Sadik","orcid":"https://orcid.org/0000-0001-8291-2211"},"institutions":[{"id":"https://openalex.org/I4210112253","display_name":"Honda (Germany)","ror":"https://ror.org/022c1xk47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210112253"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ahmed R. Sadik","raw_affiliation_strings":["Honda Research Institute Europe, Offenbach am Main, Germany"],"raw_orcid":"https://orcid.org/0000-0001-8291-2211","affiliations":[{"raw_affiliation_string":"Honda Research Institute Europe, Offenbach am Main, Germany","institution_ids":["https://openalex.org/I4210112253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5121130511","display_name":"Siddhata Govind","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112253","display_name":"Honda (Germany)","ror":"https://ror.org/022c1xk47","country_code":"DE","type":"company","lineage":["https://openalex.org/I1283473643","https://openalex.org/I4210112253"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Siddhata Govind","raw_affiliation_strings":["Honda Research Institute Europe, Offenbach am Main, Germany"],"raw_orcid":"https://orcid.org/0009-0002-6173-0667","affiliations":[{"raw_affiliation_string":"Honda Research Institute Europe, Offenbach am Main, Germany","institution_ids":["https://openalex.org/I4210112253"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.1536,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.98680182,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"969","last_page":"975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.868399977684021,"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":0.868399977684021,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.021299999207258224,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.01769999973475933,"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/benchmarking","display_name":"Benchmarking","score":0.7486000061035156},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.6791999936103821},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6549999713897705},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5260999798774719},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.483599990606308},{"id":"https://openalex.org/keywords/code-smell","display_name":"Code smell","score":0.4715999960899353}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7486000061035156},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6859999895095825},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6791999936103821},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6549999713897705},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5260999798774719},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.483599990606308},{"id":"https://openalex.org/C133237599","wikidata":"https://www.wikidata.org/wiki/Q2295111","display_name":"Code smell","level":5,"score":0.4715999960899353},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.41679999232292175},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.41339999437332153},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37720000743865967},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3614000082015991},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33489999175071716},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.3066999912261963},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C137287247","wikidata":"https://www.wikidata.org/wiki/Q1329550","display_name":"Static program analysis","level":4,"score":0.27140000462532043}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3756681.3756993","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756681.3756993","pdf_url":null,"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 29th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3756681.3756993","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3756681.3756993","pdf_url":null,"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 29th International Conference on Evaluation and Assessment in Software Engineering","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W2291952557","https://openalex.org/W2763667918","https://openalex.org/W2795218835","https://openalex.org/W2938063707","https://openalex.org/W3186629732","https://openalex.org/W4392141840","https://openalex.org/W4393032472","https://openalex.org/W4394984774","https://openalex.org/W4396788588","https://openalex.org/W4403536396","https://openalex.org/W4403607016","https://openalex.org/W4403607483","https://openalex.org/W4407243808","https://openalex.org/W6968421401"],"related_works":[],"abstract_inverted_index":{"Determining":[0],"which":[1],"Large":[2],"Language":[3],"Model":[4],"(LLM)":[5],"is":[6,12,56],"superior":[7],"for":[8,66,135,146],"code":[9,38,60,96,104,148],"smell":[10,97,105,149],"detection":[11,77,119],"a":[13,21,33],"complex":[14],"challenge.":[15],"This":[16],"study":[17],"aims":[18],"to":[19,27,138],"establish":[20],"systematic":[22],"methodology":[23],"and":[24,51,73,82,99,143],"evaluation":[25,85],"matrix":[26],"address":[28],"this":[29],"question.":[30],"We":[31,68],"introduce":[32],"curated":[34],"dataset":[35,54],"containing":[36],"smelly":[37],"implementations":[39],"of":[40,89,112],"identical":[41],"scenarios":[42],"across":[43],"four":[44],"major":[45],"programming":[46],"languages:":[47],"Java,":[48],"Python,":[49],"JavaScript,":[50],"C++.":[52],"Each":[53],"entry":[55],"annotated":[57],"with":[58],"known":[59],"smells,":[61],"serving":[62],"as":[63],"ground":[64],"truth":[65],"evaluation.":[67],"benchmark":[69],"two":[70],"state-of-the-art":[71],"LLMs\u2014DeepSeek-V3":[72],"OpenAI":[74,123],"GPT-4.0\u2014analyzing":[75],"their":[76,117],"capabilities":[78],"using":[79],"precision,":[80],"recall,":[81],"F1-score.":[83],"Our":[84],"spans":[86],"three":[87],"levels":[88],"granularity:":[90],"overall":[91],"model":[92,114],"performance,":[93],"performance":[94,101],"per":[95,102],"category,":[98],"detailed":[100],"individual":[103],"type.":[106],"Additionally,":[107],"we":[108],"assess":[109],"the":[110,140],"cost-effectiveness":[111],"each":[113],"by":[115],"considering":[116],"differing":[118],"techniques\u2014token-based":[120],"analysis":[121],"in":[122,128],"GPT-4.0":[124],"versus":[125],"pattern":[126],"matching":[127],"DeepSeek-V3.":[129],"The":[130],"findings":[131],"provide":[132],"valuable":[133],"insights":[134],"practitioners":[136],"aiming":[137],"select":[139],"most":[141],"efficient":[142],"cost-effective":[144],"LLM":[145],"automated":[147],"detection.":[150]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-24T00:00:00"}