{"id":"https://openalex.org/W4402671203","doi":"https://doi.org/10.18653/v1/2024.acl-long.802","title":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","display_name":"IRCoder: Intermediate Representations Make Language Models Robust Multilingual Code Generators","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402671203","doi":"https://doi.org/10.18653/v1/2024.acl-long.802"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.acl-long.802","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-long.802","pdf_url":"https://aclanthology.org/2024.acl-long.802.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":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.acl-long.802.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022743339","display_name":"Indraneil Paul","orcid":"https://orcid.org/0000-0001-8215-4764"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Indraneil Paul","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079336821","display_name":"Goran Glava\u009a\u0161","orcid":"https://orcid.org/0000-0002-1301-6314"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goran Glava\u0161","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5027450194","display_name":"Iryna Gurevych","orcid":"https://orcid.org/0000-0003-2187-7621"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Iryna Gurevych","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.2004,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93595085,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"15023","last_page":"15041"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.8859999775886536,"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/T12031","display_name":"Speech and dialogue systems","score":0.8859999775886536,"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":0.8780999779701233,"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/T10215","display_name":"Semantic Web and Ontologies","score":0.8123999834060669,"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/computer-science","display_name":"Computer science","score":0.7788880467414856},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5888339281082153},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5796039700508118},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5048933625221252},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.4748920500278473},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4205721616744995},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40461084246635437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7788880467414856},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5888339281082153},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5796039700508118},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5048933625221252},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.4748920500278473},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4205721616744995},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40461084246635437},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"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/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/v1/2024.acl-long.802","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-long.802","pdf_url":"https://aclanthology.org/2024.acl-long.802.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":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.acl-long.802","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.acl-long.802","pdf_url":"https://aclanthology.org/2024.acl-long.802.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":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.47999998927116394,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402671203.pdf","grobid_xml":"https://content.openalex.org/works/W4402671203.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2169518243","https://openalex.org/W4231937131","https://openalex.org/W323219885","https://openalex.org/W2063928587","https://openalex.org/W1487966966","https://openalex.org/W1589342014","https://openalex.org/W2163672025","https://openalex.org/W2258184894","https://openalex.org/W2048831961","https://openalex.org/W1606349578"],"abstract_inverted_index":{"Code":[0],"generation":[1,176],"has":[2,48],"fast":[3],"become":[4],"one":[5],"of":[6,11,19,39,76,91,108,160],"the":[7,37,44,74,88,143,148,154],"most":[8,59],"popular":[9],"applications":[10],"language":[12,56,137,150],"models":[13],"(LMs).Nonetheless,":[14],"research":[15],"on":[16,65,140],"multilingual":[17,89,183],"aspects":[18],"Code-LMs,":[20],"such":[21],"as":[22],"cross-lingual":[23],"transfer":[24],"between":[25],"different":[26],"programming":[27,85,162],"languages,":[28],"language-specific":[29],"data":[30,40],"augmentation,":[31],"and":[32,93,151,170,178,188],"post-hoc":[33],"LM":[34],"adaptation,":[35],"alongside":[36],"exploitation":[38],"sources":[41],"other":[42],"than":[43,52],"original":[45],"textual":[46],"content,":[47],"been":[49,63],"much":[50],"sparser":[51],"for":[53],"their":[54,117],"natural":[55],"counterparts.In":[57],"particular,":[58],"mainstream":[60],"Code-LMs":[61,92,125,144],"have":[62],"pre-trained":[64],"source":[66,112],"code":[67,113,175,184,186],"files":[68,114],"alone.In":[69],"this":[70,97],"work,":[71],"we":[72,99,132],"investigate":[73],"prospect":[75],"leveraging":[77],"readily":[78],"available":[79],"compiler":[80],"intermediate":[81,119],"representations":[82],"(IR)-shared":[83],"across":[84,173],"languages-to":[86],"improve":[87],"capabilities":[90],"facilitate":[94],"crosslingual":[95],"transfer.To":[96],"end,":[98],"first":[100],"compile":[101],"SLTrans,":[102,141],"1,2":[103],"a":[104],"parallel":[105],"dataset":[106],"consisting":[107],"nearly":[109],"4M":[110],"self-contained":[111],"coupled":[115],"with":[116,157],"respective":[118,158],"representations.Next,":[120],"starting":[121],"from":[122,127],"various":[123,161,174],"base":[124],"(ranging":[126],"1.1B":[128],"to":[129,145],"7.3B":[130],"parameters),":[131],"carry":[133],"out":[134],"continued":[135],"causal":[136],"modelling":[138],"training":[139],"forcing":[142],"(1)":[146],"learn":[147],"IR":[149,155],"(2)":[152],"align":[153],"constructs":[156,159],"languages.Our":[163],"resulting":[164],"models,":[165],"dubbed":[166],"IRCoder,":[167],"display":[168],"sizeable":[169],"consistent":[171],"gains":[172],"tasks":[177],"metrics,":[179],"including":[180],"prompt":[181],"robustness,":[182],"completion,":[185],"understanding,":[187],"instruction":[189],"following.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}