{"id":"https://openalex.org/W7160603592","doi":"https://doi.org/10.5753/jbcs.2026.6153","title":"\"Call My Big Sibling (CMBS)\" \u2013 A Confidence-Based Strategy Leveraging Instance Selection to Combine Small and Large Language Models for Cost-Effective Text Classification","display_name":"\"Call My Big Sibling (CMBS)\" \u2013 A Confidence-Based Strategy Leveraging Instance Selection to Combine Small and Large Language Models for Cost-Effective Text Classification","publication_year":2026,"publication_date":"2026-05-05","ids":{"openalex":"https://openalex.org/W7160603592","doi":"https://doi.org/10.5753/jbcs.2026.6153"},"language":null,"primary_location":{"id":"doi:10.5753/jbcs.2026.6153","is_oa":true,"landing_page_url":"https://doi.org/10.5753/jbcs.2026.6153","pdf_url":null,"source":{"id":"https://openalex.org/S69801987","display_name":"Journal of the Brazilian Computer Society","issn_l":"0104-6500","issn":["0104-6500","1678-4804"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Brazilian Computer Society","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5753/jbcs.2026.6153","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009156529","display_name":"Cl\u00e1udio Mois\u00e9s Valiense de Andrade","orcid":"https://orcid.org/0000-0002-7366-2633"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Claudio Mois\u00e9s Valiense de Andrade","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-7366-2633","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135704118","display_name":"Washington Cunha","orcid":"https://orcid.org/0000-0002-1988-8412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Washington Cunha","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-1988-8412","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135650160","display_name":"Davi Reis","orcid":"https://orcid.org/0009-0000-7299-1542"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davi Reis","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0000-7299-1542","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126531785","display_name":"Celso Franca","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Celso Fran\u00e7a","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-0251-7172","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135701071","display_name":"Wasterman \u00c1vila Apolin\u00e1rio","orcid":"https://orcid.org/0009-0002-9657-4887"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wasterman \u00c1vila Apolin\u00e1rio","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0002-9657-4887","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135652658","display_name":"Luana de Castro Santos","orcid":"https://orcid.org/0009-0001-2619-4152"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luana de Castro Santos","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0009-0001-2619-4152","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135690620","display_name":"Adriana Silvina Pagano","orcid":"https://orcid.org/0000-0002-3150-3503"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Adriana Silvina Pagano","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3150-3503","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135700594","display_name":"Leonardo Chaves Dutra da Rocha","orcid":"https://orcid.org/0000-0002-4913-4902"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leonardo Chaves Dutra da Rocha","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-4913-4902","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135700293","display_name":"Marcos Andr\u00e9 Gon\u00e7alves","orcid":"https://orcid.org/0000-0002-2075-3363"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Marcos Andr\u00e9 Gon\u00e7alves","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-2075-3363","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1390,"currency":"USD","value_usd":1390},"apc_paid":{"value":1390,"currency":"USD","value_usd":1390},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.56809969,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"1","first_page":"1233","last_page":"1249"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.26570001244544983,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.26570001244544983,"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/T10028","display_name":"Topic Modeling","score":0.14309999346733093,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.10920000076293945,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6060000061988831},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45350000262260437},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4230000078678131},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4050999879837036},{"id":"https://openalex.org/keywords/sibling","display_name":"Sibling","score":0.26840001344680786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7469000220298767},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6060000061988831},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5681999921798706},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5078999996185303},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45350000262260437},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4237000048160553},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4230000078678131},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3276999890804291},{"id":"https://openalex.org/C2776194465","wikidata":"https://www.wikidata.org/wiki/Q31184","display_name":"Sibling","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.26190000772476196}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5753/jbcs.2026.6153","is_oa":true,"landing_page_url":"https://doi.org/10.5753/jbcs.2026.6153","pdf_url":null,"source":{"id":"https://openalex.org/S69801987","display_name":"Journal of the Brazilian Computer Society","issn_l":"0104-6500","issn":["0104-6500","1678-4804"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Brazilian Computer Society","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.5753/jbcs.2026.6153","is_oa":true,"landing_page_url":"https://doi.org/10.5753/jbcs.2026.6153","pdf_url":null,"source":{"id":"https://openalex.org/S69801987","display_name":"Journal of the Brazilian Computer Society","issn_l":"0104-6500","issn":["0104-6500","1678-4804"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of the Brazilian Computer Society","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W1546425147","https://openalex.org/W2022322548","https://openalex.org/W2163455955","https://openalex.org/W2251939518","https://openalex.org/W2295077356","https://openalex.org/W2566927129","https://openalex.org/W2621166576","https://openalex.org/W2916132663","https://openalex.org/W2963341956","https://openalex.org/W2963809228","https://openalex.org/W3022371575","https://openalex.org/W3094560306","https://openalex.org/W3126191299","https://openalex.org/W3208426488","https://openalex.org/W4285129823","https://openalex.org/W4317904898","https://openalex.org/W4365459368","https://openalex.org/W4366277658","https://openalex.org/W4384639909","https://openalex.org/W4387337551","https://openalex.org/W4389519914","https://openalex.org/W4400391132","https://openalex.org/W4401042286","https://openalex.org/W4401880751","https://openalex.org/W4402671080","https://openalex.org/W4404534353","https://openalex.org/W4411120260","https://openalex.org/W4412544568","https://openalex.org/W4412945513","https://openalex.org/W4414925442","https://openalex.org/W7131827440"],"related_works":[],"abstract_inverted_index":{"Transformers":[0,23],"have":[1],"achieved":[2],"state-of-the-art":[3],"results,":[4],"with":[5,50,81],"Large":[6],"Language":[7,26],"Models":[8],"(LLMs)":[9],"leading":[10],"many":[11],"NLP":[12,165],"tasks.":[13],"However,":[14],"it":[15],"remains":[16],"unclear":[17],"whether":[18],"LLMs":[19,53,75,113],"always":[20],"outperform":[21,78],"first-generation":[22],"(aka":[24],"Small":[25],"Models,":[27],"SLMs)":[28],"across":[29,59],"different":[30],"text":[31],"classification":[32,65],"tasks":[33],"and":[34,62,85,111,150],"scenarios":[35],"(e.g.,":[36],"movie":[37],"reviews,":[38],"topic":[39,64],"classification).":[40],"This":[41],"study":[42],"compares":[43],"four":[44,51,63],"SLMs":[45,82,110,149],"(BERT,":[46],"RoBERTa,":[47],"Qwen,":[48],"BART)":[49],"open":[52,74,112],"(LLaMA":[54],"3.1,":[55],"Mistral,":[56],"Falcon,":[57],"DeepSeek)":[58],"nine":[60],"sentiment":[61],"datasets,":[66],"totaling":[67],"over":[68],"1000":[69],"results.":[70],"Results":[71],"show":[72,145],"that":[73,107],"only":[76],"moderately":[77],"or":[79,138],"tie":[80],"when":[83],"fine-tuned,":[84],"at":[86,154],"a":[87,103,155,161],"very":[88],"high":[89],"computational":[90],"cost.":[91],"To":[92],"address":[93],"this":[94],"trade-off,":[95],"we":[96],"propose":[97],"\u201cCall":[98],"My":[99],"Big":[100],"Sibling\u201d":[101],"(CMBS),":[102],"novel":[104],"confidence-based":[105],"framework":[106],"integrates":[108],"calibrated":[109],"using":[114],"advanced":[115],"instance":[116],"selection":[117],"techniques.":[118],"CMBS":[119,146],"assigns":[120],"high-confidence":[121],"instances":[122,129],"to":[123,132],"the":[124,158],"cheaper":[125],"SLM,":[126],"while":[127],"low-confidence":[128],"are":[130],"routed":[131],"an":[133],"LLM":[134],"in":[135],"zero-shot,":[136],"in-context,":[137],"partially":[139],"tuned":[140],"modes,":[141],"optimizing":[142],"cost-effectiveness.":[143],"Experiments":[144],"significantly":[147],"outperforms":[148],"delivers":[151],"LLM-level":[152],"performance":[153],"fraction":[156],"of":[157],"cost,":[159],"offering":[160],"cost-sensitive":[162],"solution":[163],"for":[164],"applications.":[166]},"counts_by_year":[],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2026-05-09T00:00:00"}