{"id":"https://openalex.org/W4388650545","doi":"https://doi.org/10.1145/3604237.3626891","title":"Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking","display_name":"Making LLMs Worth Every Penny: Resource-Limited Text Classification in Banking","publication_year":2023,"publication_date":"2023-11-25","ids":{"openalex":"https://openalex.org/W4388650545","doi":"https://doi.org/10.1145/3604237.3626891"},"language":"en","primary_location":{"id":"doi:10.1145/3604237.3626891","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604237.3626891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2311.06102","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5017613411","display_name":"Lefteris Loukas","orcid":"https://orcid.org/0000-0002-7473-9428"},"institutions":[{"id":"https://openalex.org/I4210154887","display_name":"Helbio (Greece)","ror":"https://ror.org/050a0jp38","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210154887"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Lefteris Loukas","raw_affiliation_strings":["Helvia.ai, Greece"],"raw_orcid":"https://orcid.org/0000-0002-7473-9428","affiliations":[{"raw_affiliation_string":"Helvia.ai, Greece","institution_ids":["https://openalex.org/I4210154887"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092720860","display_name":"Ilias Stogiannidis","orcid":"https://orcid.org/0009-0005-5803-1138"},"institutions":[{"id":"https://openalex.org/I4210154887","display_name":"Helbio (Greece)","ror":"https://ror.org/050a0jp38","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210154887"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Ilias Stogiannidis","raw_affiliation_strings":["Helvia.ai, Greece"],"raw_orcid":"https://orcid.org/0009-0005-5803-1138","affiliations":[{"raw_affiliation_string":"Helvia.ai, Greece","institution_ids":["https://openalex.org/I4210154887"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093257097","display_name":"Odysseas Diamantopoulos","orcid":null},"institutions":[{"id":"https://openalex.org/I4210154887","display_name":"Helbio (Greece)","ror":"https://ror.org/050a0jp38","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210154887"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Odysseas Diamantopoulos","raw_affiliation_strings":["Helvia.ai, Greece"],"raw_orcid":"https://orcid.org/0009-0009-0830-4512","affiliations":[{"raw_affiliation_string":"Helvia.ai, Greece","institution_ids":["https://openalex.org/I4210154887"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016618602","display_name":"Prodromos Malakasiotis","orcid":"https://orcid.org/0009-0008-0055-5598"},"institutions":[{"id":"https://openalex.org/I73142707","display_name":"Athens University of Economics and Business","ror":"https://ror.org/03s262162","country_code":"GR","type":"education","lineage":["https://openalex.org/I73142707"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Prodromos Malakasiotis","raw_affiliation_strings":["Athens University of Economics and Business, Greece"],"raw_orcid":"https://orcid.org/0009-0008-0055-5598","affiliations":[{"raw_affiliation_string":"Athens University of Economics and Business, Greece","institution_ids":["https://openalex.org/I73142707"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084667235","display_name":"Stavros Vassos","orcid":"https://orcid.org/0000-0001-7564-5290"},"institutions":[{"id":"https://openalex.org/I4210154887","display_name":"Helbio (Greece)","ror":"https://ror.org/050a0jp38","country_code":"GR","type":"company","lineage":["https://openalex.org/I4210154887"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Stavros Vassos","raw_affiliation_strings":["Helvia.ai, Greece"],"raw_orcid":"https://orcid.org/0000-0001-7564-5290","affiliations":[{"raw_affiliation_string":"Helvia.ai, Greece","institution_ids":["https://openalex.org/I4210154887"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2755,"has_fulltext":true,"cited_by_count":33,"citation_normalized_percentile":{"value":0.96354554,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"392","last_page":"400"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9850999712944031,"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":0.9807000160217285,"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/computer-science","display_name":"Computer science","score":0.6489149332046509},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6446728706359863},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6212348341941833},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5240695476531982},{"id":"https://openalex.org/keywords/shot","display_name":"Shot (pellet)","score":0.4787801504135132},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.475766122341156},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.464988648891449},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.45892977714538574},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4513992369174957},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.42683130502700806},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4190451502799988},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.35158324241638184},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33941930532455444}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6489149332046509},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6446728706359863},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6212348341941833},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5240695476531982},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.4787801504135132},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.475766122341156},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.464988648891449},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.45892977714538574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4513992369174957},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.42683130502700806},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4190451502799988},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.35158324241638184},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33941930532455444},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3604237.3626891","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3604237.3626891","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"4th ACM International Conference on AI in Finance","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2311.06102","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.06102","pdf_url":"https://arxiv.org/pdf/2311.06102","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2311.06102","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.06102","pdf_url":"https://arxiv.org/pdf/2311.06102","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8751572122","display_name":"An Interactive, Collaborative Digital Gamification Approach to Effective Experiential Training and Prediction of Criminal Actions","funder_award_id":"101021714","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388650545.pdf","grobid_xml":"https://content.openalex.org/works/W4388650545.grobid-xml"},"referenced_works_count":47,"referenced_works":["https://openalex.org/W2106411961","https://openalex.org/W2786860129","https://openalex.org/W2891177506","https://openalex.org/W2914304175","https://openalex.org/W2949676527","https://openalex.org/W2963341956","https://openalex.org/W2965373594","https://openalex.org/W2966087730","https://openalex.org/W2970597249","https://openalex.org/W2986193249","https://openalex.org/W3005680577","https://openalex.org/W3016473712","https://openalex.org/W3027879771","https://openalex.org/W3034368386","https://openalex.org/W3045492832","https://openalex.org/W3106092787","https://openalex.org/W3122241445","https://openalex.org/W3138154797","https://openalex.org/W3153451655","https://openalex.org/W3156669901","https://openalex.org/W3160638507","https://openalex.org/W3167376363","https://openalex.org/W3198599617","https://openalex.org/W4205991051","https://openalex.org/W4206729293","https://openalex.org/W4221143046","https://openalex.org/W4226278401","https://openalex.org/W4243739713","https://openalex.org/W4285137661","https://openalex.org/W4285263469","https://openalex.org/W4285310604","https://openalex.org/W4285333908","https://openalex.org/W4287867774","https://openalex.org/W4292779060","https://openalex.org/W4296959557","https://openalex.org/W4297683418","https://openalex.org/W4312651322","https://openalex.org/W4321392130","https://openalex.org/W4327810158","https://openalex.org/W4384918448","https://openalex.org/W4385245566","https://openalex.org/W4385573009","https://openalex.org/W4385573636","https://openalex.org/W4385574438","https://openalex.org/W4386303029","https://openalex.org/W4389523909","https://openalex.org/W4391876619"],"related_works":["https://openalex.org/W2074502265","https://openalex.org/W4214877189","https://openalex.org/W2773965352","https://openalex.org/W2381179799","https://openalex.org/W2786391746","https://openalex.org/W4381430104","https://openalex.org/W2995102745","https://openalex.org/W4226059458","https://openalex.org/W2914559142","https://openalex.org/W1990237101"],"abstract_inverted_index":{"Standard":[0],"Full-Data":[1],"classifiers":[2],"in":[3,13,96,147],"NLP":[4],"demand":[5],"thousands":[6],"of":[7,57,88,100,162],"labeled":[8],"examples,":[9],"which":[10],"is":[11],"impractical":[12],"data-limited":[14,148],"domains.":[15],"Few-shot":[16],"methods":[17,59],"offer":[18],"an":[19],"alternative,":[20],"utilizing":[21],"contrastive":[22],"learning":[23],"techniques":[24],"that":[25],"can":[26,44],"be":[27],"effective":[28],"with":[29,47,107,165],"as":[30,32],"little":[31],"20":[33],"examples":[34,50],"per":[35,51],"class.":[36,52],"Similarly,":[37],"Large":[38],"Language":[39],"Models":[40],"(LLMs)":[41],"like":[42],"GPT-4":[43],"perform":[45],"effectively":[46],"just":[48],"1-5":[49],"However,":[53],"the":[54,75,79,86,105],"performance-cost":[55],"trade-offs":[56],"these":[58],"remain":[60],"underexplored,":[61],"a":[62,97,112,137,157],"critical":[63],"concern":[64],"for":[65,116],"budget-limited":[66],"organizations.":[67],"Our":[68],"work":[69],"addresses":[70],"this":[71],"gap":[72],"by":[73,91],"studying":[74],"aforementioned":[76],"approaches":[77],"over":[78],"Banking77":[80],"financial":[81],"intent":[82],"detection":[83],"dataset,":[84],"including":[85],"evaluation":[87],"cutting-edge":[89],"LLMs":[90,117],"OpenAI,":[92],"Cohere,":[93],"and":[94,135],"Anthropic":[95],"comprehensive":[98],"set":[99],"few-shot":[101,133],"scenarios.":[102,149],"We":[103],"complete":[104],"picture":[106],"two":[108],"additional":[109],"methods:":[110],"first,":[111],"cost-effective":[113],"querying":[114],"method":[115,140],"based":[118],"on":[119],"retrieval-augmented":[120],"generation":[121],"(RAG),":[122],"able":[123,143],"to":[124,131,144,151],"reduce":[125],"operational":[126],"costs":[127],"multiple":[128],"times":[129],"compared":[130],"classic":[132],"approaches,":[134],"second,":[136],"data":[138],"augmentation":[139],"using":[141],"GPT-4,":[142],"improve":[145],"performance":[146],"Finally,":[150],"inspire":[152],"future":[153],"research,":[154],"we":[155],"provide":[156],"human":[158],"expert\u2019s":[159],"curated":[160],"subset":[161],"Banking77,":[163],"along":[164],"extensive":[166],"error":[167],"analysis.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":19}],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2025-10-10T00:00:00"}