{"id":"https://openalex.org/W7140130829","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.148","title":"Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification","display_name":"Better as Generators Than Classifiers: Leveraging LLMs and Synthetic Data for Low-Resource Multilingual Classification","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140130829","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.148"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.148","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.148","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.148","pdf_url":"https://aclanthology.org/2026.findings-eacl.148.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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: EACL 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.findings-eacl.148.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078389036","display_name":"Branislav Pecher","orcid":"https://orcid.org/0000-0003-0344-8620","observed_orcids":["https://orcid.org/0000-0003-0344-8620"]},"institutions":[{"id":"https://openalex.org/I4401200340","display_name":"Kempelen Institute of Intelligent Technologies","ror":"https://ror.org/02j78kr76","country_code":"SK","type":"nonprofit","lineage":["https://openalex.org/I4401200340"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Branislav Pecher","raw_affiliation_strings":["Kempelen Institute of Intelligent Technologies , Bratislava , Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kempelen Institute of Intelligent Technologies , Bratislava , Slovakia","institution_ids":["https://openalex.org/I4401200340"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081841143","display_name":"J\u00e1n \u010cegi\u0148","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401200340","display_name":"Kempelen Institute of Intelligent Technologies","ror":"https://ror.org/02j78kr76","country_code":"SK","type":"nonprofit","lineage":["https://openalex.org/I4401200340"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Jan Cegin","raw_affiliation_strings":["Kempelen Institute of Intelligent Technologies , Bratislava , Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kempelen Institute of Intelligent Technologies , Bratislava , Slovakia","institution_ids":["https://openalex.org/I4401200340"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123879130","display_name":"Robert Belanec","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I60587646","display_name":"Brno University of Technology","ror":"https://ror.org/03613d656","country_code":"CZ","type":"education","lineage":["https://openalex.org/I60587646"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Robert Belanec","raw_affiliation_strings":["Faculty of Information Technology , Brno University of Technology , Brno , Czechia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Faculty of Information Technology , Brno University of Technology , Brno , Czechia","institution_ids":["https://openalex.org/I60587646"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082763244","display_name":"Ivan Srba","orcid":"https://orcid.org/0000-0003-3511-5337","observed_orcids":["https://orcid.org/0000-0003-3511-5337"]},"institutions":[{"id":"https://openalex.org/I4401200340","display_name":"Kempelen Institute of Intelligent Technologies","ror":"https://ror.org/02j78kr76","country_code":"SK","type":"nonprofit","lineage":["https://openalex.org/I4401200340"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Ivan Srba","raw_affiliation_strings":["Kempelen Institute of Intelligent Technologies , Bratislava , Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kempelen Institute of Intelligent Technologies , Bratislava , Slovakia","institution_ids":["https://openalex.org/I4401200340"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043199710","display_name":"Jakub \u0160imko","orcid":"https://orcid.org/0000-0003-0239-4237","observed_orcids":["https://orcid.org/0000-0003-0239-4237"]},"institutions":[{"id":"https://openalex.org/I4401200340","display_name":"Kempelen Institute of Intelligent Technologies","ror":"https://ror.org/02j78kr76","country_code":"SK","type":"nonprofit","lineage":["https://openalex.org/I4401200340"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Jakub Simko","raw_affiliation_strings":["Kempelen Institute of Intelligent Technologies , Bratislava , Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kempelen Institute of Intelligent Technologies , Bratislava , Slovakia","institution_ids":["https://openalex.org/I4401200340"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030414237","display_name":"M\u00e1ria Bielikov\u00e1","orcid":"https://orcid.org/0000-0003-4105-3494","observed_orcids":["https://orcid.org/0000-0003-4105-3494"]},"institutions":[{"id":"https://openalex.org/I4401200340","display_name":"Kempelen Institute of Intelligent Technologies","ror":"https://ror.org/02j78kr76","country_code":"SK","type":"nonprofit","lineage":["https://openalex.org/I4401200340"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Maria Bielikova","raw_affiliation_strings":["Kempelen Institute of Intelligent Technologies , Bratislava , Slovakia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kempelen Institute of Intelligent Technologies , Bratislava , Slovakia","institution_ids":["https://openalex.org/I4401200340"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.15014685,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2840","last_page":"2857"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8687000274658203,"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":0.8687000274658203,"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":0.06390000134706497,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.053700000047683716,"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/large-language-models","display_name":"large language models","score":0.7310000061988831},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.949999988079071},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.7720000147819519},{"id":"https://openalex.org/keywords/multilingual-classification","display_name":"multilingual classification","score":0.9399999976158142},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":0.9950000047683716},{"id":"https://openalex.org/keywords/synthetic-data-augmentation","display_name":"synthetic data augmentation","score":0.38100001215934753},{"id":"https://openalex.org/keywords/instruction-tuning","display_name":"instruction tuning","score":0.625},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.8410000205039978},{"id":"https://openalex.org/keywords/in-context-learning","display_name":"in-context learning","score":0.746999979019165},{"id":"https://openalex.org/keywords/multilingual-llms","display_name":"multilingual LLMs","score":0.6650000214576721}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5651999711990356},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.426800012588501},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.34380000829696655},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3012999892234802},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2386000007390976},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.23659999668598175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.148","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.148","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.148","pdf_url":"https://aclanthology.org/2026.findings-eacl.148.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.148","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.148","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.148","pdf_url":"https://aclanthology.org/2026.findings-eacl.148.pdf","source":{"id":"https://openalex.org/S7407087051","display_name":"Findings of the Association for Computational Linguistics: EACL","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"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: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140130829.pdf","grobid_xml":"https://content.openalex.org/works/W7140130829.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160101653","https://openalex.org/W4416036701","https://openalex.org/W4387322747","https://openalex.org/W4402671762","https://openalex.org/W7165198664","https://openalex.org/W4417298833","https://openalex.org/W4416037553","https://openalex.org/W4404088094","https://openalex.org/W7215011477","https://openalex.org/W4407310657"],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"multilingual":[7,83,161],"capabilities,":[8],"making":[9],"them":[10],"promising":[11],"tools":[12],"in":[13,34,136],"both":[14],"high-and":[15],"low-resource":[16,35,137],"languages.One":[17],"particularly":[18,135],"valuable":[19],"use":[20,80],"case":[21],"is":[22,40],"generating":[23],"synthetic":[24,48,87,111,124],"samples":[25],"that":[26,62,119,142,155],"can":[27,52],"be":[28],"used":[29,99],"to":[30,85,100,129],"train":[31,101],"smaller":[32,60,102,127,157],"models":[33,61,103,128],"scenarios":[36],"where":[37],"human-labelled":[38],"data":[39,49,125,154],"scarce.In":[41],"this":[42,77],"work,":[43],"we":[44,79],"investigate":[45],"whether":[46],"these":[47],"generation":[50],"capabilities":[51],"serve":[53],"as":[54,110,147],"a":[55,81],"form":[56],"of":[57,123],"distillation,":[58],"producing":[59,153],"perform":[63],"on":[64],"par":[65],"with":[66],"or":[67,106,109],"even":[68,120],"better":[69],"than":[70,151],"massive":[71],"LLMs":[72,143],"across":[73],"languages":[74,91],"and":[75,92,158],"tasks.To":[76],"end,":[78],"state-ofthe-art":[82],"LLM":[84],"generate":[86],"datasets":[88,96],"covering":[89],"11":[90],"4":[93],"classification":[94],"tasks.These":[95],"are":[97,144],"then":[98],"via":[104],"fine-tuning":[105],"instruction":[107],"tuning,":[108],"in-context":[112],"examples":[113],"for":[114],"compact":[115],"LLMs.Our":[116],"experiments":[117],"show":[118],"small":[121],"amounts":[122],"enable":[126],"outperform":[130],"the":[131,139],"large":[132],"generator":[133],"itself,":[134],"languages.Overall,":[138],"results":[140],"suggest":[141],"best":[145],"utilised":[146],"generators":[148],"(teachers)":[149],"rather":[150],"classifiers,":[152],"empowers":[156],"more":[159],"efficient":[160],"models.":[162]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-03-24T00:00:00"}