{"id":"https://openalex.org/W4387947295","doi":"https://doi.org/10.48550/arxiv.2310.15539","title":"SteloCoder: a Decoder-Only LLM for Multi-Language to Python Code Translation","display_name":"SteloCoder: a Decoder-Only LLM for Multi-Language to Python Code Translation","publication_year":2023,"publication_date":"2023-10-24","ids":{"openalex":"https://openalex.org/W4387947295","doi":"https://doi.org/10.48550/arxiv.2310.15539"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2310.15539","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.15539","pdf_url":"https://arxiv.org/pdf/2310.15539","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2310.15539","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111062790","display_name":"Jialing Pan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pan, Jialing","raw_affiliation_strings":["Esperanto Technologies Inc","Stanford University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Esperanto Technologies Inc","institution_ids":[]},{"raw_affiliation_string":"Stanford University","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093126686","display_name":"Adrien Sad\u00e9","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sad\u00e9, Adrien","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100380870","display_name":"Jin Kim","orcid":"https://orcid.org/0000-0002-5013-3958","observed_orcids":["https://orcid.org/0000-0002-5013-3958"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kim, Jin","raw_affiliation_strings":["Esperanto Technologies Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Esperanto Technologies Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125674287","display_name":"Eric Soriano","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soriano, Eric","raw_affiliation_strings":["Esperanto Technologies Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Esperanto Technologies Inc","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011345211","display_name":"Guillem Sole","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sole, Guillem","raw_affiliation_strings":["Esperanto Technologies Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Esperanto Technologies Inc","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5093126688","display_name":"Sylvain Flamant","orcid":"https://orcid.org/0009-0004-3135-4853","observed_orcids":["https://orcid.org/0009-0004-3135-4853"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Flamant, Sylvain","raw_affiliation_strings":["Esperanto Technologies Inc"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Esperanto Technologies Inc","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":36,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9839000105857849,"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":0.9839000105857849,"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/T10028","display_name":"Topic Modeling","score":0.010900000110268593,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.002899999963119626,"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/code-translation","display_name":"program translation","score":0.7360000014305115},{"id":"https://openalex.org/keywords/starcoder","display_name":"StarCoder","score":0.7620000243186951},{"id":"https://openalex.org/keywords/decoder-only-llms","display_name":"decoder-only LLMs","score":0.7519999742507935},{"id":"https://openalex.org/keywords/mixture-of-experts","display_name":"mixture of experts","score":0.8809999823570251},{"id":"https://openalex.org/keywords/lora","display_name":"LoRa","score":0.8130000233650208},{"id":"https://openalex.org/keywords/curriculum-learning","display_name":"curriculum learning","score":0.9160000085830688},{"id":"https://openalex.org/keywords/efficient-training","display_name":"efficient training","score":0.5120000243186951},{"id":"https://openalex.org/keywords/programming-language-translation","display_name":"programming language translation","score":0.5360000133514404}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.9396748542785645},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8572628498077393},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6497709155082703},{"id":"https://openalex.org/C544833334","wikidata":"https://www.wikidata.org/wiki/Q2005","display_name":"JavaScript","level":2,"score":0.6481056213378906},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.6187705397605896},{"id":"https://openalex.org/C203005215","wikidata":"https://www.wikidata.org/wiki/Q79798","display_name":"Machine translation","level":2,"score":0.5593130588531494},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5264687538146973},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.4394860863685608},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39754411578178406},{"id":"https://openalex.org/C78519656","wikidata":"https://www.wikidata.org/wiki/Q101333","display_name":"Mechanical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2310.15539","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.15539","pdf_url":"https://arxiv.org/pdf/2310.15539","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2310.15539","doi":"https://doi.org/10.48550/arxiv.2310.15539","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2310.15539","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2310.15539","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.15539","pdf_url":"https://arxiv.org/pdf/2310.15539","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4387947295.pdf","grobid_xml":"https://content.openalex.org/works/W4387947295.grobid-xml"},"referenced_works_count":5,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2296073425","https://openalex.org/W2741838462","https://openalex.org/W3089307846","https://openalex.org/W4283210053"],"related_works":["https://openalex.org/W7155086535","https://openalex.org/W4409796840","https://openalex.org/W7132936884","https://openalex.org/W4401201888","https://openalex.org/W7152552103","https://openalex.org/W4415796065","https://openalex.org/W4417153283","https://openalex.org/W4411233265","https://openalex.org/W4399197902","https://openalex.org/W4403486628"],"abstract_inverted_index":{"With":[0,170],"the":[1,77,130,188,192,210],"recent":[2],"focus":[3],"on":[4,164,172,218],"Large":[5],"Language":[6],"Models":[7],"(LLMs),":[8],"both":[9],"StarCoder":[10,83,106,208],"(Li":[11],"et":[12,19],"al.,":[13,20],"2023)":[14,21],"and":[15,95,146,212],"Code":[16],"Llama":[17],"(Rozi\u00e8re":[18],"have":[22],"demonstrated":[23],"remarkable":[24],"performance":[25,190],"in":[26,37,137,183],"code":[27,38,61,73,225],"generation.":[28],"However,":[29],"there":[30],"is":[31,200,226],"still":[32],"a":[33,52,88,96,111,154],"need":[34],"for":[35,58,99,150],"improvement":[36],"translation":[39,74],"functionality":[40],"with":[41,207],"efficient":[42,151],"training":[43,135,217],"techniques.":[44],"In":[45,63],"response":[46],"to":[47,133,162,202],"this,":[48],"we":[49,109,141],"introduce":[50],"SteloCoder,":[51],"decoder-only":[53],"StarCoder-based":[54],"LLM":[55],"designed":[56],"specifically":[57],"multi-programming":[59,184],"language-to-Python":[60,185],"translation.":[62],"particular,":[64],"SteloCoder":[65,175],"achieves":[66,176],"C++,":[67],"C#,":[68],"JavaScript,":[69],"Java,":[70],"or":[71],"PHP-to-Python":[72],"without":[75],"specifying":[76],"input":[78],"programming":[79],"language.":[80],"We":[81],"modified":[82],"model":[84],"architecture":[85],"by":[86,105,194],"incorporating":[87],"Mixture-of-Experts":[89],"(MoE)":[90],"technique":[91],"featuring":[92],"five":[93],"experts":[94],"gating":[97],"network":[98],"multi-task":[100],"handling.":[101],"Experts":[102],"are":[103],"obtained":[104],"fine-tuning.":[107,152],"Specifically,":[108],"use":[110,147],"Low-Rank":[112],"Adaptive":[113],"Method":[114],"(LoRA)":[115],"technique,":[116],"limiting":[117],"each":[118,156],"expert":[119,157],"size":[120],"as":[121,209],"only":[122,159,203],"0.06%":[123],"of":[124,126,139,179,215],"number":[125],"StarCoder's":[127],"parameters.":[128],"At":[129],"same":[131],"time,":[132,140],"enhance":[134],"efficiency":[136],"terms":[138],"adopt":[142],"curriculum":[143],"learning":[144],"strategy":[145],"self-instruct":[148],"data":[149],"As":[153],"result,":[155],"takes":[158],"6":[160],"hours":[161,214],"train":[163],"one":[165,219],"single":[166],"80Gb":[167],"A100":[168,221],"HBM.":[169,222],"experiments":[171],"XLCoST":[173],"datasets,":[174],"an":[177],"average":[178],"73.76":[180],"CodeBLEU":[181],"score":[182],"translation,":[186],"surpassing":[187],"top":[189],"from":[191],"leaderboard":[193],"at":[195],"least":[196],"3.5.":[197],"This":[198],"accomplishment":[199],"attributed":[201],"45M":[204],"extra":[205],"parameters":[206],"backbone":[211],"32":[213],"valid":[216],"80GB":[220],"The":[223],"source":[224],"release":[227],"here:":[228],"https://github.com/sade-adrien/SteloCoder.":[229]},"counts_by_year":[{"year":2026,"cited_by_count":13},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":9}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-10-26T00:00:00"}