{"id":"https://openalex.org/W4389518608","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.187","title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","display_name":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389518608","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.187"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.emnlp-main.187","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.187","pdf_url":"https://aclanthology.org/2023.emnlp-main.187.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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.emnlp-main.187.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100330243","display_name":"Minghao Li","orcid":"https://orcid.org/0000-0001-5490-2024","observed_orcids":["https://orcid.org/0000-0001-5490-2024","https://orcid.org/0009-0005-3328-012X"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghao Li","raw_affiliation_strings":["Alibaba Group ,","Alibaba Group,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group ,","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group,","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022916584","display_name":"Yingxiu Zhao","orcid":"https://orcid.org/0000-0001-8236-3486","observed_orcids":["https://orcid.org/0000-0001-8236-3486"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yingxiu Zhao","raw_affiliation_strings":["Hong Kong University of Science and Technology ,","Hong Kong University of Science and Technology,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hong Kong University of Science and Technology ,","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"Hong Kong University of Science and Technology,","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101188063","display_name":"Bowen Yu","orcid":"https://orcid.org/0009-0008-9642-7880","observed_orcids":["https://orcid.org/0009-0008-9642-7880"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Yu","raw_affiliation_strings":["Alibaba Group ,","Alibaba Group,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group ,","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group,","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059659416","display_name":"Feifan Song","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feifan Song","raw_affiliation_strings":["Peking University ,","Peking University,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Peking University ,","institution_ids":["https://openalex.org/I20231570"]},{"raw_affiliation_string":"Peking University,","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100724756","display_name":"Hangyu Li","orcid":"https://orcid.org/0000-0002-9659-3634","observed_orcids":["https://orcid.org/0000-0002-9659-3634"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hangyu Li","raw_affiliation_strings":["Alibaba Group ,","Alibaba Group,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group ,","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group,","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432190","display_name":"Haiyang Yu","orcid":"https://orcid.org/0000-0003-3313-6687","observed_orcids":["https://orcid.org/0000-0003-3313-6687"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiyang Yu","raw_affiliation_strings":["Alibaba Group ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group ,","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036786337","display_name":"Zhoujun Li","orcid":"https://orcid.org/0000-0002-9603-9713","observed_orcids":["https://orcid.org/0000-0002-9603-9713"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhoujun Li","raw_affiliation_strings":["Shenzhen Intelligent Strong Technology Co., Ltd ,","Alibaba Group,","Shenzhen Intelligent Strong Technology Co., Ltd,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shenzhen Intelligent Strong Technology Co., Ltd ,","institution_ids":[]},{"raw_affiliation_string":"Alibaba Group,","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Shenzhen Intelligent Strong Technology Co., Ltd,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100620486","display_name":"Fei Huang","orcid":"https://orcid.org/0000-0001-9665-6642","observed_orcids":["https://orcid.org/0000-0001-9665-6642","https://orcid.org/0009-0005-1326-3824","https://orcid.org/0000-0002-3709-5053","https://orcid.org/0000-0002-3805-8107"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Huang","raw_affiliation_strings":["Alibaba Group ,","Alibaba Group,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group ,","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group,","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100644428","display_name":"Yongbin Li","orcid":"https://orcid.org/0009-0008-4504-2163","observed_orcids":["https://orcid.org/0009-0008-4504-2163"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yongbin Li","raw_affiliation_strings":["Alibaba Group ,","Alibaba Group,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group ,","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Alibaba Group,","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":20.7784,"has_fulltext":true,"cited_by_count":104,"citation_normalized_percentile":{"value":0.99625132,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3102","last_page":"3116"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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/T10028","display_name":"Topic Modeling","score":0.998199999332428,"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":0.9916999936103821,"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/leverage","display_name":"Leverage (statistics)","score":0.8216332793235779},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7056236267089844},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6337224245071411},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.510426938533783},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.4813831150531769},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.42832517623901367},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.39531540870666504},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3210769295692444},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.24335521459579468},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.14963266253471375},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10389208793640137},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.06460314989089966}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.8216332793235779},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7056236267089844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6337224245071411},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.510426938533783},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4813831150531769},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.42832517623901367},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.39531540870666504},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3210769295692444},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.24335521459579468},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.14963266253471375},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10389208793640137},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.06460314989089966},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/v1/2023.emnlp-main.187","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.187","pdf_url":"https://aclanthology.org/2023.emnlp-main.187.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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-138245","is_oa":false,"landing_page_url":"http://lbdiscover.ust.hk/uresolver?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rfr_id=info:sid/HKUST:SPI&rft.genre=article&rft.issn=&rft.volume=&rft.issue=&rft.date=2023&rft.spage=3102&rft.aulast=Li&rft.aufirst=Minghao&rft.atitle=API-Bank%3A+A+Comprehensive+Benchmark+for+Tool-Augmented+LLMs&rft.title=EMNLP+2023+-+2023+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+Proceedings","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Conference paper"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.emnlp-main.187","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.187","pdf_url":"https://aclanthology.org/2023.emnlp-main.187.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 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"x_sdgs":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389518608.pdf","grobid_xml":"https://content.openalex.org/works/W4389518608.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W2091879643","https://openalex.org/W3177813494","https://openalex.org/W4226352076","https://openalex.org/W4285294723","https://openalex.org/W4292779060","https://openalex.org/W4301243929","https://openalex.org/W4304195432","https://openalex.org/W4309088836","https://openalex.org/W4312091890","https://openalex.org/W4320165837","https://openalex.org/W4321177655","https://openalex.org/W4322718191","https://openalex.org/W4327810433","https://openalex.org/W4360836968","https://openalex.org/W4366328015","https://openalex.org/W4377371656","https://openalex.org/W4377865087","https://openalex.org/W4378474282","https://openalex.org/W4378509421","https://openalex.org/W4378713418","https://openalex.org/W4378718568","https://openalex.org/W4380136738","https://openalex.org/W4382173325","https://openalex.org/W4383046813","https://openalex.org/W4385474529","https://openalex.org/W4385775236","https://openalex.org/W4388626886"],"related_works":["https://openalex.org/W2366107444","https://openalex.org/W2378211422","https://openalex.org/W4388145910","https://openalex.org/W1976205134","https://openalex.org/W2381570729","https://openalex.org/W2745001401","https://openalex.org/W4248336175","https://openalex.org/W4321353415","https://openalex.org/W3009369890","https://openalex.org/W2358812761"],"abstract_inverted_index":{"Recent":[0],"research":[1,178],"has":[2],"demonstrated":[3],"that":[4,130],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"can":[9,32],"enhance":[10,34],"their":[11],"capabilities":[12,90],"by":[13,158],"utilizing":[14,29],"external":[15],"tools.However,":[16],"three":[17],"pivotal":[18],"questions":[19],"remain":[20],"unanswered:":[21],"(1)":[22],"How":[23,31],"effective":[24],"are":[25],"current":[26],"LLMs":[27],"in":[28,91,142,179],"tools?(2)":[30],"we":[33,52,66,100,119,171],"LLMs'":[35,89],"ability":[36],"to":[37,43,46,85,137,182],"utilize":[38],"tools?(3)":[39],"What":[40],"obstacles":[41],"need":[42],"be":[44],"overcome":[45],"leverage":[47],"tools?To":[48],"address":[49],"these":[50],"questions,":[51],"introduce":[53],"API-Bank,":[54],"a":[55,68,102,122],"groundbreaking":[56],"benchmark,":[57],"specifically":[58],"designed":[59],"for":[60,149,176],"tool-augmented":[61,123],"LLMs.For":[62],"the":[63,87,97,165,173,184],"first":[64],"question,":[65,99],"develop":[67],"runnable":[69],"evaluation":[70],"system":[71],"consisting":[72],"of":[73,167],"73":[74],"API":[75,83],"tools.We":[76],"annotate":[77],"314":[78],"tool-use":[79,108],"dialogues":[80,109],"with":[81],"753":[82],"calls":[84],"assess":[86],"existing":[88],"planning,":[92],"retrieving,":[93],"and":[94,163],"calling":[95],"APIs.For":[96],"second":[98],"construct":[101],"comprehensive":[103],"training":[104],"set":[105],"containing":[106],"1,888":[107],"from":[110,126],"2,138":[111],"APIs":[112],"spanning":[113],"1,000":[114],"distinct":[115],"domains.Using":[116],"this":[117,180],"dataset,":[118],"train":[120],"Lynx,":[121],"LLM":[124],"initialized":[125],"Alpaca.Experimental":[127],"results":[128],"demonstrate":[129],"GPT-3.5":[131],"exhibits":[132],"improved":[133],"tool":[134,155],"utilization":[135,156],"compared":[136],"GPT-3,":[138],"while":[139],"GPT-4":[140],"excels":[141],"planning.However,":[143],"there":[144],"is":[145],"still":[146],"significant":[147],"potential":[148],"further":[150],"improvement.Moreover,":[151],"Lynx":[152],"surpasses":[153],"Alpaca's":[154],"performance":[157],"more":[159],"than":[160],"26":[161],"pts":[162],"approaches":[164],"effectiveness":[166],"GPT-3.5.Through":[168],"error":[169],"analysis,":[170],"highlight":[172],"key":[174],"challenges":[175],"future":[177],"field":[181],"answer":[183],"third":[185],"question":[186],"1":[187],".":[188]},"counts_by_year":[{"year":2026,"cited_by_count":46},{"year":2025,"cited_by_count":45},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":1}],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2025-10-10T00:00:00"}