{"id":"https://openalex.org/W4416034748","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.296","title":"Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation","display_name":"Use Random Selection for Now: Investigation of Few-Shot Selection Strategies in LLM-based Text Augmentation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4416034748","doi":"https://doi.org/10.18653/v1/2025.findings-emnlp.296"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.296","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.296","pdf_url":"https://aclanthology.org/2025.findings-emnlp.296.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: EMNLP 2025","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.findings-emnlp.296.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5081841143","display_name":"J\u00e1n \u010cegi\u0148","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jan Cegin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078389036","display_name":"Branislav Pecher","orcid":"https://orcid.org/0000-0003-0344-8620"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Branislav Pecher","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043199710","display_name":"Jakub \u0160imko","orcid":"https://orcid.org/0000-0003-0239-4237"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jakub Simko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082763244","display_name":"Ivan Srba","orcid":"https://orcid.org/0000-0003-3511-5337"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ivan Srba","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030414237","display_name":"M\u00e1ria Bielikov\u00e1","orcid":"https://orcid.org/0000-0003-4105-3494"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Maria Bielikova","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5037674585","display_name":"Peter Brusilovsky","orcid":"https://orcid.org/0000-0002-1902-1464"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peter Brusilovsky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.29973403,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5533","last_page":"5550"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6694999933242798,"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":0.6694999933242798,"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":0.13510000705718994,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.04340000078082085,"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/selection","display_name":"Selection (genetic algorithm)","score":0.6413000226020813},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.40389999747276306},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.27810001373291016},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.2662000060081482}],"concepts":[{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6413000226020813},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5792999863624573},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5457000136375427},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.40389999747276306},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3700000047683716},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24799999594688416},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2337000072002411}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.findings-emnlp.296","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.296","pdf_url":"https://aclanthology.org/2025.findings-emnlp.296.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: EMNLP 2025","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.findings-emnlp.296","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.findings-emnlp.296","pdf_url":"https://aclanthology.org/2025.findings-emnlp.296.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: EMNLP 2025","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3931493262","display_name":"Improving scientific excellence and creativity in combating disinformation with artificial intelligence and language technologies","funder_award_id":"101079164","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G6948331134","display_name":null,"funder_award_id":"APVV-22-","funder_id":"https://openalex.org/F4320323251","funder_display_name":"Agent\u00fara na Podporu V\u00fdskumu a V\u00fdvoja"},{"id":"https://openalex.org/G7999996730","display_name":"Multimod\u00e1lna detekcia prejavov toxick\u00e9ho spr\u00e1vania v soci\u00e1lnych m\u00e9di\u00e1ch","funder_award_id":"APVV-22-0414","funder_id":"https://openalex.org/F4320323251","funder_display_name":"Agent\u00fara na Podporu V\u00fdskumu a V\u00fdvoja"},{"id":"https://openalex.org/G941802975","display_name":null,"funder_award_id":"90254","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"},{"id":"https://openalex.org/F4320323251","display_name":"Agent\u00fara na Podporu V\u00fdskumu a V\u00fdvoja","ror":"https://ror.org/037nx0e70"},{"id":"https://openalex.org/F4320334322","display_name":"HORIZON EUROPE Framework Programme","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416034748.pdf","grobid_xml":"https://content.openalex.org/works/W4416034748.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"generative":[1],"large":[2],"language":[3],"models":[4],"(LLMs)":[5],"are":[6,16,37,45,125],"increasingly":[7],"used":[8,23],"for":[9,24,31,111,137],"data":[10],"augmentation":[11,85,138],"tasks,":[12],"where":[13],"text":[14],"samples":[15,44],"paraphrased":[17],"(or":[18],"generated":[19],"anew)":[20],"and":[21,49,78,94,118],"then":[22],"downstream":[25],"model":[26,96],"fine-tuning.This":[27],"is":[28,63],"useful,":[29],"especially":[30,110],"low-resource":[32,88],"settings.For":[33],"better":[34],"augmentations,":[35],"LLMs":[36],"prompted":[38],"with":[39,119],"examples":[40],"(few-shot":[41],"scenarios).Yet,":[42],"the":[43,54,74,106],"mostly":[46],"selected":[47],"randomly,":[48],"a":[50,87,127,134],"comprehensive":[51],"overview":[52],"of":[53,56,108,129],"effects":[55,81],"other":[57],"(more":[58],"\"informed\")":[59],"sample":[60,69,131],"selection":[61,70,103,132],"strategies":[62,71,104],"lacking.In":[64],"this":[65,91],"work,":[66],"we":[67],"compare":[68],"existing":[72],"in":[73,82,86],"few-shot":[75],"learning":[76],"literature":[77],"investigate":[79],"their":[80],"LLMbased":[83],"textual":[84],"setting.We":[89],"evaluate":[90],"on":[92],"in-distribution":[93],"out-of-distribution":[95,112],"performance.Results":[97],"indicate":[98],"that":[99],"while":[100],"some":[101],"\"informed\"":[102],"increase":[105],"performance":[107,121],"models,":[109],"data,":[113],"it":[114],"happens":[115],"only":[116],"seldom":[117],"marginal":[120],"increases.Unless":[122],"further":[123],"advances":[124],"made,":[126],"default":[128],"random":[130],"remains":[133],"good":[135],"option":[136],"practitioners.":[139]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-08T00:00:00"}