{"id":"https://openalex.org/W4415249770","doi":"https://doi.org/10.1109/icmla66185.2025.00085","title":"Code Generation with Small Language Models: A Codeforces-Based Study","display_name":"Code Generation with Small Language Models: A Codeforces-Based Study","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4415249770","doi":"https://doi.org/10.1109/icmla66185.2025.00085"},"language":"en","primary_location":{"id":"doi:10.1109/icmla66185.2025.00085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2504.07343","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007561405","display_name":"D\u00e9bora Souza","orcid":"https://orcid.org/0000-0001-9147-6183"},"institutions":[{"id":"https://openalex.org/I41455075","display_name":"Universidade Federal de Campina Grande","ror":"https://ror.org/00eftnx64","country_code":"BR","type":"education","lineage":["https://openalex.org/I41455075"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"D\u00e9bora Souza","raw_affiliation_strings":["Federal University of Campina Grande,Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Campina Grande,Brazil","institution_ids":["https://openalex.org/I41455075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075988425","display_name":"Rohit Gheyi","orcid":"https://orcid.org/0000-0002-5562-4449"},"institutions":[{"id":"https://openalex.org/I41455075","display_name":"Universidade Federal de Campina Grande","ror":"https://ror.org/00eftnx64","country_code":"BR","type":"education","lineage":["https://openalex.org/I41455075"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Rohit Gheyi","raw_affiliation_strings":["Federal University of Campina Grande,Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Campina Grande,Brazil","institution_ids":["https://openalex.org/I41455075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109756740","display_name":"Lucas Albuquerque","orcid":null},"institutions":[{"id":"https://openalex.org/I41455075","display_name":"Universidade Federal de Campina Grande","ror":"https://ror.org/00eftnx64","country_code":"BR","type":"education","lineage":["https://openalex.org/I41455075"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Lucas Albuquerque","raw_affiliation_strings":["Federal University of Campina Grande,Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Campina Grande,Brazil","institution_ids":["https://openalex.org/I41455075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025062647","display_name":"Gustavo Soares","orcid":"https://orcid.org/0000-0002-8061-9000"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gustavo Soares","raw_affiliation_strings":["Microsoft,USA"],"affiliations":[{"raw_affiliation_string":"Microsoft,USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051287042","display_name":"M\u00e1rcio Ribeiro","orcid":"https://orcid.org/0000-0002-4293-4261"},"institutions":[{"id":"https://openalex.org/I79889768","display_name":"Universidade Federal de Alagoas","ror":"https://ror.org/00dna7t83","country_code":"BR","type":"education","lineage":["https://openalex.org/I79889768"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"M\u00e1rcio Ribeiro","raw_affiliation_strings":["Federal University of Alagoas,Brazil"],"affiliations":[{"raw_affiliation_string":"Federal University of Alagoas,Brazil","institution_ids":["https://openalex.org/I79889768"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5007561405"],"corresponding_institution_ids":["https://openalex.org/I41455075"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15020806,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"582","last_page":"587"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9695000052452087,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9695000052452087,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12031","display_name":"Speech and dialogue systems","score":0.9296000003814697,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/python","display_name":"Python (programming language)","score":0.8001999855041504},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.558899998664856},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.3878999948501587},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.38589999079704285},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.37610000371932983},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.34060001373291016}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8001999855041504},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.717199981212616},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6861000061035156},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.38589999079704285},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.37610000371932983},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3758000135421753},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.3303999900817871},{"id":"https://openalex.org/C2776187449","wikidata":"https://www.wikidata.org/wiki/Q1513879","display_name":"Natural language generation","level":3,"score":0.3303000032901764},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3221000134944916},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.31520000100135803},{"id":"https://openalex.org/C19024347","wikidata":"https://www.wikidata.org/wiki/Q211496","display_name":"High-level programming language","level":3,"score":0.2808000147342682},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.275299996137619},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27070000767707825},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2524999976158142}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icmla66185.2025.00085","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icmla66185.2025.00085","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Machine Learning and Applications (ICMLA)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.07343","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.07343","pdf_url":"https://arxiv.org/pdf/2504.07343","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},{"id":"doi:10.48550/arxiv.2504.07343","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.07343","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2504.07343","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2504.07343","pdf_url":"https://arxiv.org/pdf/2504.07343","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1,26],"Models":[2,27],"(LLMs)":[3],"demonstrate":[4],"capabilities":[5],"in":[6,59],"code":[7],"generation,":[8],"potentially":[9],"boosting":[10],"developer":[11],"productivity.":[12],"However,":[13],"their":[14],"adoption":[15],"remains":[16,62],"limited":[17],"by":[18],"high":[19],"computational":[20],"costs,":[21],"among":[22],"other":[23],"factors.":[24],"Small":[25],"(SLMs)":[28],"present":[29],"a":[30,105],"lightweight":[31],"alternative.":[32],"While":[33],"LLMs":[34],"have":[35],"been":[36],"evaluated":[37],"on":[38],"competitive":[39],"programming":[40],"tasks,":[41],"prior":[42],"work":[43],"often":[44],"emphasizes":[45],"metrics":[46],"like":[47],"Elo":[48,79],"or":[49],"pass":[50],"rates,":[51],"neglecting":[52],"failure":[53],"analysis.":[54],"The":[55],"potential":[56],"of":[57,107],"SLMs":[58],"this":[60,65],"space":[61],"underexplored.":[63],"In":[64],"study,":[66],"we":[67],"benchmark":[68],"three":[69],"open":[70],"SLMs\u2014Llama-3.2-3B,":[71],"Gemma-3-12B,":[72],"and":[73,85,114],"Phi-4-14B\u2014across":[74],"280":[75],"Codeforces":[76],"problems":[77],"spanning":[78],"ratings":[80],"from":[81,129],"800":[82],"to":[83,120],"2100":[84],"covering":[86],"36":[87],"distinct":[88],"topics.":[89],"All":[90],"models":[91],"were":[92],"tasked":[93],"with":[94,104],"generating":[95],"Python":[96,113],"solutions.":[97],"Phi-4-14B":[98],"achieved":[99],"the":[100],"best":[101],"SLM":[102],"performance":[103],"pass@3":[106],"63.6%,":[108],"nearing":[109],"o3-mini-high":[110],"(86.8%).":[111],"Combining":[112],"C++":[115],"outputs":[116],"increased":[117],"Phi-4-14B\u2019s":[118],"pass@6":[119],"73.6%.":[121],"A":[122],"qualitative":[123],"analysis":[124],"revealed":[125],"some":[126],"failures":[127],"stemmed":[128],"minor":[130],"implementation":[131],"issues":[132],"rather":[133],"than":[134],"reasoning":[135],"flaws.":[136]},"counts_by_year":[],"updated_date":"2026-04-09T06:08:40.794217","created_date":"2025-10-16T00:00:00"}