{"id":"https://openalex.org/W4389519979","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.89","title":"Execution-Based Evaluation for Open-Domain Code Generation","display_name":"Execution-Based Evaluation for Open-Domain Code Generation","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389519979","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.89"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.89","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.89","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.89","pdf_url":"https://aclanthology.org/2023.findings-emnlp.89.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.findings-emnlp.89.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059929869","display_name":"Zhiruo Wang","orcid":"https://orcid.org/0000-0002-9839-8410","observed_orcids":["https://orcid.org/0000-0002-9839-8410"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhiruo Wang","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113920761","display_name":"Shuyan Zhou","orcid":"https://orcid.org/0009-0002-8868-7996","observed_orcids":["https://orcid.org/0009-0002-8868-7996","https://orcid.org/0009-0003-1532-4542"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuyan Zhou","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003637850","display_name":"Daniel Fried","orcid":"https://orcid.org/0000-0002-5327-2558","observed_orcids":["https://orcid.org/0000-0002-5327-2558"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel Fried","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068811427","display_name":"Graham Neubig","orcid":"https://orcid.org/0000-0002-2072-3789","observed_orcids":["https://orcid.org/0000-0002-2072-3789"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Graham Neubig","raw_affiliation_strings":["Language Technologies Institute, Carnegie Mellon University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Language Technologies Institute, Carnegie Mellon University","institution_ids":["https://openalex.org/I74973139"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74973139"],"apc_list":null,"apc_paid":null,"fwci":5.1289,"has_fulltext":true,"cited_by_count":20,"citation_normalized_percentile":{"value":0.96807749,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1271","last_page":"1290"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.98580002784729,"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":0.98580002784729,"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":0.0071000000461936,"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":0.0026000000070780516,"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/multilingual-code-generation","display_name":"multilingual code generation","score":0.6520000100135803},{"id":"https://openalex.org/keywords/codex","display_name":"codices","score":0.5569999814033508},{"id":"https://openalex.org/keywords/codegen","display_name":"CodeGen","score":0.7260000109672546},{"id":"https://openalex.org/keywords/model-size-scaling","display_name":"model size scaling","score":0.5929999947547913},{"id":"https://openalex.org/keywords/test-case-evaluation","display_name":"test case evaluation","score":0.4000000059604645}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821566641330719},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8178640604019165},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.6084157228469849},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5785151720046997},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.553800106048584},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5528945326805115},{"id":"https://openalex.org/C2993776861","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Open domain","level":3,"score":0.5434861183166504},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5070157051086426},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.5067647099494934},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4420827329158783},{"id":"https://openalex.org/C53942775","wikidata":"https://www.wikidata.org/wiki/Q1211721","display_name":"Code coverage","level":3,"score":0.43326523900032043},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.40675774216651917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34928297996520996},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.24310243129730225},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.0706741213798523},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.findings-emnlp.89","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.89","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.89","pdf_url":"https://aclanthology.org/2023.findings-emnlp.89.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2212.10481","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2212.10481","pdf_url":"https://arxiv.org/pdf/2212.10481","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2212.10481","doi":"https://doi.org/10.48550/arxiv.2212.10481","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2212.10481","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.findings-emnlp.89","doi":"https://doi.org/10.18653/v1/2023.findings-emnlp.89","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.findings-emnlp.89","pdf_url":"https://aclanthology.org/2023.findings-emnlp.89.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389519979.pdf","grobid_xml":"https://content.openalex.org/works/W4389519979.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2108325777","https://openalex.org/W2154652894","https://openalex.org/W2250342921","https://openalex.org/W2751448157","https://openalex.org/W2890867094","https://openalex.org/W2964315653","https://openalex.org/W2978835257","https://openalex.org/W3089307846","https://openalex.org/W3158635868","https://openalex.org/W3164133168","https://openalex.org/W4226287673","https://openalex.org/W4226325640","https://openalex.org/W4226485558","https://openalex.org/W4282842846","https://openalex.org/W4288057765"],"related_works":["https://openalex.org/W4385562549","https://openalex.org/W7163995441","https://openalex.org/W6929340133","https://openalex.org/W3017094847","https://openalex.org/W4281763794","https://openalex.org/W4307479317","https://openalex.org/W4393903225","https://openalex.org/W4402670580","https://openalex.org/W4309395035","https://openalex.org/W4402683806"],"abstract_inverted_index":{"To":[0],"extend":[1],"the":[2,14,127],"scope":[3],"of":[4],"coding":[5,54],"queries":[6],"to":[7,21,49,109,120],"more":[8],"realistic":[9],"settings,":[10],"we":[11],"propose":[12],"ODEX,":[13],"first":[15],"Open-Domain":[16],"EXecution-based":[17],"natural":[18,51,59],"language":[19,76],"(NL)":[20],"Python":[22],"code":[23,75,128],"generation":[24,129],"dataset.ODEX":[25],"has":[26],"945":[27],"NL-Code":[28,42],"pairs":[29,43],"spanning":[30],"79":[31],"diverse":[32],"libraries,":[33],"along":[34],"with":[35,93,111],"1,707":[36],"humanwritten":[37],"test":[38],"cases":[39],"for":[40,126],"execution.Our":[41],"are":[44],"harvested":[45],"from":[46],"StackOverflow":[47],"forums":[48],"encourage":[50],"and":[52,67,102],"practical":[53],"queries.Moreover,":[55],"ODEX":[56,119],"supports":[57],"four":[58],"languages":[60],"as":[61],"intents,":[62],"in":[63],"English,":[64],"Spanish,":[65],"Japanese,":[66],"Russian.ODEX":[68],"unveils":[69],"intriguing":[70],"behavioral":[71],"differences":[72],"among":[73],"topperforming":[74],"models":[77,96],"(LM).While":[78],"CODEX":[79,94,115],"achieves":[80],"better":[81],"overall":[82],"results,":[83],"CODE-GEN":[84],"improves":[85],"effectively":[86],"via":[87],"scaling":[88],"-CODE-GEN":[89],"6.1B":[90],"performs":[91],"comparably":[92],"12B.Both":[95],"show":[97],"substantial":[98],"gaps":[99,107,116],"between":[100],"open":[101],"closed":[103],"domains,":[104],"but":[105],"CODEGEN":[106],"tend":[108],"decrease":[110],"model":[112],"size":[113],"while":[114],"increase.We":[117],"release":[118],"facilitate":[121],"research":[122],"into":[123],"open-domain":[124],"problems":[125],"community.1":[130],"Dataset":[131],"Samples":[132],"Domain":[133],"Executable?Avg.Test":[134],"Cases":[135]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":8},{"year":2023,"cited_by_count":2}],"updated_date":"2026-10-30T12:39:25.321706","created_date":"2023-12-11T00:00:00"}