{"id":"https://openalex.org/W4412876910","doi":"https://doi.org/10.1145/3711896.3737219","title":"FinBERT2: A Specialized Bidirectional Encoder for Bridging the Gap in Finance-Specific Deployment of Large Language Models","display_name":"FinBERT2: A Specialized Bidirectional Encoder for Bridging the Gap in Finance-Specific Deployment of Large Language Models","publication_year":2025,"publication_date":"2025-08-03","ids":{"openalex":"https://openalex.org/W4412876910","doi":"https://doi.org/10.1145/3711896.3737219"},"language":"en","primary_location":{"id":"doi:10.1145/3711896.3737219","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711896.3737219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072204529","display_name":"Xuan Xu","orcid":"https://orcid.org/0009-0007-1326-4282"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xuan Xu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-1326-4282","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119175108","display_name":"Fufang Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210099020","display_name":"Beijing Biocytogen (China)","ror":"https://ror.org/01spyyb53","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fufang Wen","raw_affiliation_strings":["Beijing Value Simplex Technology Co. Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0034-7191","affiliations":[{"raw_affiliation_string":"Beijing Value Simplex Technology Co. Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210099020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062868287","display_name":"Beilin Chu","orcid":"https://orcid.org/0000-0002-3024-0983"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Beilin Chu","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3024-0983","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103645753","display_name":"Zhibing Fu","orcid":"https://orcid.org/0009-0000-3898-4306"},"institutions":[{"id":"https://openalex.org/I4210099020","display_name":"Beijing Biocytogen (China)","ror":"https://ror.org/01spyyb53","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhibing Fu","raw_affiliation_strings":["Beijing Value Simplex Technology Co. Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-3898-4306","affiliations":[{"raw_affiliation_string":"Beijing Value Simplex Technology Co. Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210099020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119175109","display_name":"Qinhong Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qinhong Lin","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-6651-2866","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiaqi Liu","orcid":"https://orcid.org/0009-0003-8058-0649"},"institutions":[{"id":"https://openalex.org/I4210099020","display_name":"Beijing Biocytogen (China)","ror":"https://ror.org/01spyyb53","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaqi Liu","raw_affiliation_strings":["Beijing Value Simplex Technology Co. Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0003-8058-0649","affiliations":[{"raw_affiliation_string":"Beijing Value Simplex Technology Co. Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210099020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119175110","display_name":"Binjie Fei","orcid":"https://orcid.org/0009-0007-9719-1147"},"institutions":[{"id":"https://openalex.org/I4210099020","display_name":"Beijing Biocytogen (China)","ror":"https://ror.org/01spyyb53","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Binjie Fei","raw_affiliation_strings":["Beijing Value Simplex Technology Co. Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-9719-1147","affiliations":[{"raw_affiliation_string":"Beijing Value Simplex Technology Co. Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210099020"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yu Li","orcid":"https://orcid.org/0009-0001-5528-7606"},"institutions":[{"id":"https://openalex.org/I4210099020","display_name":"Beijing Biocytogen (China)","ror":"https://ror.org/01spyyb53","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210099020"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Li","raw_affiliation_strings":["Beijing Value Simplex Technology Co. Ltd., Beijing, China"],"raw_orcid":"https://orcid.org/0009-0001-5528-7606","affiliations":[{"raw_affiliation_string":"Beijing Value Simplex Technology Co. Ltd., Beijing, China","institution_ids":["https://openalex.org/I4210099020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059744997","display_name":"Linna Zhou","orcid":"https://orcid.org/0009-0004-0727-2436"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linna Zhou","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0727-2436","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020864189","display_name":"Zhongliang Yang","orcid":"https://orcid.org/0000-0002-8027-9560"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongliang Yang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8027-9560","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5072204529"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":8.693,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97403882,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"5117","last_page":"5128"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9941999912261963,"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/T11326","display_name":"Stock Market Forecasting Methods","score":0.9927999973297119,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/bridging","display_name":"Bridging (networking)","score":0.911140501499176},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.717983603477478},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6315525770187378},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5762720704078674},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.22308075428009033},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.15848901867866516},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07564309239387512}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.911140501499176},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.717983603477478},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6315525770187378},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5762720704078674},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.22308075428009033},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.15848901867866516},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07564309239387512}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3711896.3737219","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3711896.3737219","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17","score":0.4099999964237213}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2121879602","https://openalex.org/W2952370363","https://openalex.org/W2963341956","https://openalex.org/W3027879771","https://openalex.org/W3036320503","https://openalex.org/W3098468692","https://openalex.org/W3099700870","https://openalex.org/W4298110867","https://openalex.org/W4306403191","https://openalex.org/W4379259169","https://openalex.org/W4385572770","https://openalex.org/W4386576685","https://openalex.org/W4387847108","https://openalex.org/W4393160654","https://openalex.org/W4400525612","https://openalex.org/W4402670489","https://openalex.org/W4404351498","https://openalex.org/W4412886823","https://openalex.org/W6600474606","https://openalex.org/W6941258058"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2770234245","https://openalex.org/W96612179","https://openalex.org/W4408719353","https://openalex.org/W4229499248","https://openalex.org/W4388870064","https://openalex.org/W2566006169","https://openalex.org/W2210139803"],"abstract_inverted_index":{"In":[0],"natural":[1],"language":[2,12,19],"processing":[3],"(NLP),":[4],"the":[5,29,121,141,144,150,212,245],"focus":[6],"has":[7,32],"shifted":[8],"from":[9],"encoder-only":[10],"tiny":[11],"models":[13,129,156,179,229],"like":[14],"BERT":[15,43,228],"to":[16,74],"decoder-only":[17],"large":[18],"models(LLMs)":[20],"such":[21,53,99],"as":[22,54,100],"GPT-3.":[23],"However,":[24],"LLMs'":[25],"practical":[26,238],"application":[27],"in":[28,58,95,143,244],"financial":[30,59,125,173,202,222,227],"sector":[31],"revealed":[33],"three":[34],"limitations:":[35],"(1)":[36,153],"LLMs":[37,148,166,235,246],"often":[38],"perform":[39],"worse":[40],"than":[41],"fine-tuned":[42,155,178],"on":[44,63,68,86,111,169,207],"discriminative":[45],"tasks":[46,65],"despite":[47],"costing":[48],"much":[49],"higher":[50],"computational":[51],"resources,":[52],"market":[55],"sentiment":[56],"analysis":[57,232],"reports;":[60],"(2)":[61,176],"Application":[62],"generative":[64],"heavily":[66],"relies":[67],"retrieval":[69,88,203],"augmented":[70],"generation":[71],"(RAG)":[72],"methods":[73],"provide":[75],"current":[76],"and":[77,164,190,218,236],"specialized":[78,107],"information,":[79],"with":[80,233],"general":[81],"retrievers":[82],"showing":[83],"suboptimal":[84],"performance":[85],"domain-specific":[87],"tasks;":[89,204],"(3)":[90,205],"There":[91],"are":[92],"additional":[93],"inadequacies":[94],"other":[96,159],"feature-based":[97],"scenarios,":[98],"topic":[101,219],"modeling.":[102],"We":[103],"introduce":[104],"FinBERT2,":[105],"a":[106,112,135],"bidirectional":[108],"encoder":[109],"pretrained":[110],"high-quality,":[113],"financial-specific":[114,145],"corpus":[115,127],"of":[116,130,147],"32b":[117],"tokens.":[118],"This":[119],"represents":[120],"largest":[122],"known":[123],"Chinese":[124],"pretraining":[126],"for":[128,221,240],"this":[131],"parameter":[132],"size.":[133],"As":[134],"better":[136],"backbone,":[137],"FinBERT2":[138,208],"can":[139],"bridge":[140],"gap":[142],"deployment":[146],"through":[149,230],"following":[151],"achievements:":[152],"Discriminative":[154],"(Fin-Labelers)":[157],"outperform":[158,181],"(Fin)BERT":[160],"variants":[161],"by":[162,167],"0.4%-3.3%":[163],"leading":[165],"9.7%-12.3%":[168],"average":[170],"across":[171,200],"five":[172,201],"classification":[174],"tasks.":[175],"Contrastive":[177],"(Fin-Retrievers)":[180],"both":[182],"open-source":[183],"(e.g.,":[184,192],"+6.8%":[185],"avg":[186,194],"improvement":[187,195],"over":[188,196],"BGE-base-zh)":[189],"proprietary":[191],"+4.2%":[193],"OpenAI's":[197],"text-embedding-3-large)":[198],"embedders":[199],"Building":[206],"variants,":[209],"we":[210],"construct":[211],"Fin-TopicModel,":[213],"which":[214],"enables":[215],"superior":[216],"clustering":[217],"representation":[220],"titles.":[223],"Our":[224],"work":[225],"revisits":[226],"comparative":[231],"contemporary":[234],"offers":[237],"insights":[239],"effectively":[241],"utilizing":[242],"FinBERT":[243],"era.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}