{"id":"https://openalex.org/W4402670293","doi":"https://doi.org/10.18653/v1/2024.findings-acl.337","title":"Benchmarking Large Language Models on CFLUE - A Chinese Financial Language Understanding Evaluation Dataset","display_name":"Benchmarking Large Language Models on CFLUE - A Chinese Financial Language Understanding Evaluation Dataset","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402670293","doi":"https://doi.org/10.18653/v1/2024.findings-acl.337"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2024.findings-acl.337","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-acl.337","pdf_url":"https://aclanthology.org/2024.findings-acl.337.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":"Findings of the Association for Computational Linguistics ACL 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2024.findings-acl.337.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111249708","display_name":"Jie Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Jie Zhu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101676299","display_name":"Junhui Li","orcid":"https://orcid.org/0000-0003-3295-6050"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Junhui Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113392188","display_name":"Yalong Wen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yalong Wen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5056415939","display_name":"Lifan Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lifan Guo","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5111249708"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.8184,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.91017833,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"5673","last_page":"5693"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.7918999791145325,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11326","display_name":"Stock Market Forecasting Methods","score":0.7918999791145325,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.7010999917984009,"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":0.6822999715805054,"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/benchmarking","display_name":"Benchmarking","score":0.8555831909179688},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6454759240150452},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45041346549987793},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.43815428018569946},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3529837727546692},{"id":"https://openalex.org/keywords/business","display_name":"Business","score":0.20089977979660034}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8555831909179688},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6454759240150452},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45041346549987793},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.43815428018569946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3529837727546692},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.20089977979660034},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2024.findings-acl.337","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-acl.337","pdf_url":"https://aclanthology.org/2024.findings-acl.337.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":"Findings of the Association for Computational Linguistics ACL 2024","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2024.findings-acl.337","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2024.findings-acl.337","pdf_url":"https://aclanthology.org/2024.findings-acl.337.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":"Findings of the Association for Computational Linguistics ACL 2024","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4402670293.pdf","grobid_xml":"https://content.openalex.org/works/W4402670293.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W2059640416","https://openalex.org/W1490753184","https://openalex.org/W2284465472","https://openalex.org/W2291782699","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"light":[1],"of":[2,32,51,71,98,120,187],"recent":[3],"breakthroughs":[4],"in":[5,136,151,184],"large":[6],"language":[7,14],"models":[8],"(LLMs)":[9],"that":[10,125,143,178],"have":[11],"revolutionized":[12],"natural":[13],"processing":[15],"(NLP),":[16],"there":[17,144],"is":[18,145,174],"an":[19,132],"urgent":[20],"need":[21],"for":[22,60,139,149],"new":[23],"benchmarks":[24],"to":[25,47],"keep":[26],"pace":[27],"with":[28,75,194],"the":[29,39,49,162,181],"fast":[30],"development":[31],"LLMs.In":[33,153],"this":[34],"paper,":[35],"we":[36,115],"propose":[37],"CFLUE,":[38,114],"Chinese":[40],"Financial":[41],"Language":[42],"Understanding":[43],"Evaluation":[44],"benchmark,":[45],"designed":[46],"assess":[48],"capability":[50],"LLMs":[52,173],"across":[53,95],"various":[54],"dimensions.Specifically,":[55],"CFLUE":[56,90,195],"provides":[57],"datasets":[58,190],"tailored":[59],"both":[61],"knowledge":[62,67,140],"assessment":[63],"and":[64,85,111,129,158,191],"application":[65,88,154],"assessment.In":[66],"assessment,":[68,89,141,155],"it":[69],"consists":[70],"38K+":[72],"multiple-choice":[73],"questions":[74,79],"associated":[76,193],"solution":[77],"explanations.These":[78],"serve":[80],"dual":[81],"purposes:":[82],"answer":[83,137],"prediction":[84,138],"question":[86],"reasoning.In":[87],"features":[91],"16K+":[92],"test":[93],"instances":[94],"distinct":[96],"groups":[97],"NLP":[99],"tasks":[100],"such":[101],"as":[102,161],"text":[103,112],"classification,":[104],"machine":[105],"translation,":[106],"relation":[107],"extraction,":[108],"reading":[109],"comprehension,":[110],"generation.Upon":[113],"conduct":[116],"a":[117],"thorough":[118],"evaluation":[119],"representative":[121],"LLMs.The":[122],"results":[123],"reveal":[124],"only":[126],"Qwen-72B,":[127],"GPT-4,":[128],"GPT-4-turbo":[130],"achieve":[131],"accuracy":[133],"exceeding":[134],"60%":[135],"suggesting":[142],"still":[146],"substantial":[147],"room":[148],"improvement":[150],"current":[152],"while":[156],"GPT-4":[157],"GPT-4turbo":[159],"rank":[160],"top":[163],"two":[164],"performers":[165],"on":[166],"average,":[167],"their":[168],"significant":[169],"advantage":[170],"over":[171],"opensource":[172],"noticeably":[175],"diminished,":[176],"given":[177],"Qwen-72B":[179],"achieves":[180],"best":[182],"performance":[183],"2":[185],"out":[186],"5":[188],"tasks.The":[189],"scripts":[192],"are":[196],"openly":[197],"accessible":[198],"at":[199],"https://github.com/aliyun/cflue.":[200]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3}],"updated_date":"2026-04-23T09:07:50.710637","created_date":"2025-10-10T00:00:00"}