{"id":"https://openalex.org/W4389524484","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.859","title":"CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code","display_name":"CodeBERTScore: Evaluating Code Generation with Pretrained Models of Code","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389524484","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.859"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.emnlp-main.859","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.859","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.859","pdf_url":"https://aclanthology.org/2023.emnlp-main.859.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2023.emnlp-main.859.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","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/A5107243336","display_name":"Uri Alon","orcid":"https://orcid.org/0000-0001-5796-9988","observed_orcids":["https://orcid.org/0000-0001-5796-9988"]},"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":"Uri Alon","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/A5076309222","display_name":"Sumit D. Agarwal","orcid":"https://orcid.org/0000-0002-8305-3786","observed_orcids":["https://orcid.org/0000-0002-8305-3786"]},"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":"Sumit Agarwal","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":36.5412,"has_fulltext":true,"cited_by_count":193,"citation_normalized_percentile":{"value":0.99835609,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"13921","last_page":"13937"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9955999851226807,"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":0.9955999851226807,"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":0.0027000000700354576,"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":0.0003000000142492354,"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-generation-evaluation","display_name":"code generation evaluation","score":0.9020000100135803},{"id":"https://openalex.org/keywords/bertscore","display_name":"BERTScore","score":0.9539999961853027},{"id":"https://openalex.org/keywords/natural-language-to-code","display_name":"natural language to code","score":0.7070000171661377},{"id":"https://openalex.org/keywords/evaluation-indicators","display_name":"evaluation metrics","score":0.6800000071525574},{"id":"https://openalex.org/keywords/functional-correctness","display_name":"functional correctness","score":0.9259999990463257},{"id":"https://openalex.org/keywords/programming-languages","display_name":"programming languages","score":0.4909999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8608359098434448},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.6237863302230835},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5865843296051025},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.5712357759475708},{"id":"https://openalex.org/C151578736","wikidata":"https://www.wikidata.org/wiki/Q1251793","display_name":"Redundant code","level":4,"score":0.5595584511756897},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.548431396484375},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.502098798751831},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.48886674642562866},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4841671586036682},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4411843717098236},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.43128007650375366},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3718159794807434},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3645075559616089},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"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},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2023.emnlp-main.859","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.859","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.859","pdf_url":"https://aclanthology.org/2023.emnlp-main.859.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2302.05527","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2302.05527","pdf_url":"https://arxiv.org/pdf/2302.05527","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.2302.05527","doi":"https://doi.org/10.48550/arxiv.2302.05527","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2302.05527","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.emnlp-main.859","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.859","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.859","pdf_url":"https://aclanthology.org/2023.emnlp-main.859.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320338294","display_name":"Air Force Research Laboratory","ror":"https://ror.org/02e2egq70"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389524484.pdf","grobid_xml":"https://content.openalex.org/works/W4389524484.grobid-xml"},"referenced_works_count":29,"referenced_works":["https://openalex.org/W2101105183","https://openalex.org/W2123301721","https://openalex.org/W2126793110","https://openalex.org/W2148190602","https://openalex.org/W2154652894","https://openalex.org/W2936695845","https://openalex.org/W2946417913","https://openalex.org/W2963341956","https://openalex.org/W2964315653","https://openalex.org/W2980282514","https://openalex.org/W3017961061","https://openalex.org/W3089307846","https://openalex.org/W3098605233","https://openalex.org/W3177813494","https://openalex.org/W3195140297","https://openalex.org/W4224060952","https://openalex.org/W4226287673","https://openalex.org/W4281763794","https://openalex.org/W4285483825","https://openalex.org/W4303443398","https://openalex.org/W4307479317","https://openalex.org/W4309395035","https://openalex.org/W4309804142","https://openalex.org/W4313563421","https://openalex.org/W4315706637","https://openalex.org/W4366204357","https://openalex.org/W4375859932","https://openalex.org/W4389519979","https://openalex.org/W4389524038"],"related_works":["https://openalex.org/W4402516191","https://openalex.org/W4396764454","https://openalex.org/W4385573348","https://openalex.org/W4375859932","https://openalex.org/W7126383469","https://openalex.org/W4375947047","https://openalex.org/W4328028680","https://openalex.org/W4404782360","https://openalex.org/W4385571808","https://openalex.org/W3008088841"],"abstract_inverted_index":{"Since":[0],"the":[1,22,54,63,68,73,76,163],"rise":[2],"of":[3,21,51,91],"neural":[4],"natural-language-tocode":[5],"models":[6,145,154],"(NL\u2192Code)":[7],"that":[8,98,118],"can":[9],"generate":[10],"long":[11],"expressions":[12],"and":[13,79,107],"statements":[14],"rather":[15],"than":[16,111,159],"a":[17,101,120],"single":[18],"next-token,":[19],"one":[20],"major":[23],"problems":[24],"has":[25],"been":[26,156],"reliably":[27],"evaluating":[28],"their":[29],"generated":[30,55,69,77,116],"output.In":[31],"this":[32],"paper,":[33],"we":[34],"propose":[35],"CodeBERTScore:":[36],"an":[37,88],"evaluation":[38,90],"metric":[39],"for":[40],"code":[41,78,117],"generation,":[42],"which":[43],"builds":[44],"on":[45],"BERTScore":[46],"(Zhang":[47],"et":[48],"al.,":[49],"2020).Instead":[50],"encoding":[52],"only":[53],"tokens":[56],"as":[57,85,133,135],"in":[58],"BERTScore,":[59],"CodeBERTScore":[60,92],"also":[61],"encodes":[62],"natural":[64,82],"language":[65,83],"input":[66],"preceding":[67],"code,":[70],"thus":[71],"modeling":[72],"consistency":[74],"between":[75],"its":[80],"given":[81],"context":[84],"well.We":[86],"perform":[87],"extensive":[89],"across":[93],"four":[94],"programming":[95],"languages.We":[96],"find":[97],"Code-BERTScore":[99,124],"achieves":[100],"higher":[102,121],"correlation":[103],"with":[104,108,148],"human":[105],"preference":[106],"functional":[109],"correctness":[110],"all":[112],"existing":[113],"metrics.That":[114],"is,":[115],"receives":[119],"score":[122],"by":[123,131],"is":[125],"more":[126,158],"likely":[127],"to":[128,136,146],"be":[129],"preferred":[130],"humans,":[132],"well":[134],"function":[137],"correctly":[138],"when":[139],"executed.We":[140],"release":[141],"five":[142],"language-specific":[143,153],"pretrained":[144],"use":[147],"our":[149],"publicly":[150],"available":[151],"code.Our":[152],"have":[155],"downloaded":[157],"1,000,000":[160],"times":[161],"from":[162],"Huggingface":[164],"Hub.":[165],"1":[166]},"counts_by_year":[{"year":2026,"cited_by_count":54},{"year":2025,"cited_by_count":79},{"year":2024,"cited_by_count":41},{"year":2023,"cited_by_count":19}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2023-12-11T00:00:00"}