{"id":"https://openalex.org/W4411974633","doi":"https://doi.org/10.1007/s00607-025-01518-8","title":"LLM synthetic generation to enhance online content moderation generalization in hate speech scenarios","display_name":"LLM synthetic generation to enhance online content moderation generalization in hate speech scenarios","publication_year":2025,"publication_date":"2025-07-03","ids":{"openalex":"https://openalex.org/W4411974633","doi":"https://doi.org/10.1007/s00607-025-01518-8"},"language":"en","primary_location":{"id":"doi:10.1007/s00607-025-01518-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00607-025-01518-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00607-025-01518-8.pdf","source":{"id":"https://openalex.org/S35593046","display_name":"Computing","issn_l":"0010-485X","issn":["0010-485X","1436-5057"],"is_oa":false,"is_in_doaj":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s00607-025-01518-8.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114711529","display_name":"Adri\u00e1n Gir\u00f3n","orcid":"https://orcid.org/0009-0000-2419-3570"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Adri\u00e1n Gir\u00f3n","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040465870","display_name":"Javier Huertas\u2010Tato","orcid":"https://orcid.org/0000-0003-4127-5505"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Javier Huertas-Tato","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025314362","display_name":"David Camacho","orcid":"https://orcid.org/0000-0002-5051-3475"},"institutions":[{"id":"https://openalex.org/I88060688","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02","country_code":"ES","type":"education","lineage":["https://openalex.org/I88060688"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"David Camacho","raw_affiliation_strings":["Universidad Polit\u00e9cnica de Madrid, Madrid, Spain"],"affiliations":[{"raw_affiliation_string":"Universidad Polit\u00e9cnica de Madrid, Madrid, Spain","institution_ids":["https://openalex.org/I88060688"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114711529"],"corresponding_institution_ids":["https://openalex.org/I88060688"],"apc_list":{"value":2290,"currency":"EUR","value_usd":2890},"apc_paid":{"value":2290,"currency":"EUR","value_usd":2890},"fwci":8.9133,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.97431074,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"107","issue":"8","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9997000098228455,"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/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9997000098228455,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9386000037193298,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9265999794006348,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/generalization","display_name":"Generalization","score":0.7197471261024475},{"id":"https://openalex.org/keywords/moderation","display_name":"Moderation","score":0.6424615979194641},{"id":"https://openalex.org/keywords/content","display_name":"Content (measure theory)","score":0.5726772546768188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5410666465759277},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4623604416847229},{"id":"https://openalex.org/keywords/content-analysis","display_name":"Content analysis","score":0.45904937386512756},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4087703824043274},{"id":"https://openalex.org/keywords/multimedia","display_name":"Multimedia","score":0.3389219045639038},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2680056691169739},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.1620701253414154},{"id":"https://openalex.org/keywords/sociology","display_name":"Sociology","score":0.09292030334472656}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7197471261024475},{"id":"https://openalex.org/C93225998","wikidata":"https://www.wikidata.org/wiki/Q1941972","display_name":"Moderation","level":2,"score":0.6424615979194641},{"id":"https://openalex.org/C2778152352","wikidata":"https://www.wikidata.org/wiki/Q5165061","display_name":"Content (measure theory)","level":2,"score":0.5726772546768188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5410666465759277},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4623604416847229},{"id":"https://openalex.org/C162446236","wikidata":"https://www.wikidata.org/wiki/Q653137","display_name":"Content analysis","level":2,"score":0.45904937386512756},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4087703824043274},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.3389219045639038},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2680056691169739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1620701253414154},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.09292030334472656},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s00607-025-01518-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00607-025-01518-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00607-025-01518-8.pdf","source":{"id":"https://openalex.org/S35593046","display_name":"Computing","issn_l":"0010-485X","issn":["0010-485X","1436-5057"],"is_oa":false,"is_in_doaj":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s00607-025-01518-8","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s00607-025-01518-8","pdf_url":"https://link.springer.com/content/pdf/10.1007/s00607-025-01518-8.pdf","source":{"id":"https://openalex.org/S35593046","display_name":"Computing","issn_l":"0010-485X","issn":["0010-485X","1436-5057"],"is_oa":false,"is_in_doaj":false,"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1664884391","display_name":null,"funder_award_id":"RS-2023-00267476","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"},{"id":"https://openalex.org/G3911141858","display_name":null,"funder_award_id":"TEC-2024/COM-404","funder_id":"https://openalex.org/F4320313831","funder_display_name":"Comunidad de Madrid"},{"id":"https://openalex.org/G8461633894","display_name":null,"funder_award_id":"101168344","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G8892191124","display_name":null,"funder_award_id":"DIGITAL-2023-DEPLOY- 04-EDMO-HUBS 101158511","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G916158222","display_name":null,"funder_award_id":"RS-2023-00267476","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320313831","display_name":"Comunidad de Madrid","ror":null},{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320322138","display_name":"Universidad Polit\u00e9cnica de Madrid","ror":"https://ror.org/03n6nwv02"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411974633.pdf","grobid_xml":"https://content.openalex.org/works/W4411974633.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W2064675550","https://openalex.org/W2251882135","https://openalex.org/W2767899794","https://openalex.org/W2811439929","https://openalex.org/W2896457183","https://openalex.org/W2954566102","https://openalex.org/W2956090150","https://openalex.org/W2963216553","https://openalex.org/W2963545917","https://openalex.org/W2971296908","https://openalex.org/W3035682985","https://openalex.org/W3036167779","https://openalex.org/W3105959138","https://openalex.org/W3107176549","https://openalex.org/W3153451655","https://openalex.org/W3170644058","https://openalex.org/W3172299815","https://openalex.org/W3174057701","https://openalex.org/W3174828871","https://openalex.org/W4200580493","https://openalex.org/W4206192262","https://openalex.org/W4206500717","https://openalex.org/W4285210452","https://openalex.org/W4287829148","https://openalex.org/W4317897818","https://openalex.org/W4372048971","https://openalex.org/W4385245566","https://openalex.org/W4385569878","https://openalex.org/W4385570289","https://openalex.org/W4385573325","https://openalex.org/W4385573369","https://openalex.org/W4385573937","https://openalex.org/W4387436025","https://openalex.org/W4387579388","https://openalex.org/W4388788876","https://openalex.org/W4389519059","https://openalex.org/W4399695140","https://openalex.org/W4408015891","https://openalex.org/W6604896550","https://openalex.org/W6610385870","https://openalex.org/W6756688054","https://openalex.org/W6851092083"],"related_works":["https://openalex.org/W2740268725","https://openalex.org/W3093710306","https://openalex.org/W750217911","https://openalex.org/W4206949499","https://openalex.org/W2296969234","https://openalex.org/W4226254121","https://openalex.org/W4388229525","https://openalex.org/W131533274","https://openalex.org/W1912037221","https://openalex.org/W2568448309"],"abstract_inverted_index":{"Abstract":[0],"As":[1],"social":[2],"media":[3],"and":[4,23,96,152,157,191,224,244,265,282],"digital":[5],"platforms":[6],"become":[7],"more":[8,158],"influential,":[9],"the":[10,35,47,91,126,135,166,177,278],"spread":[11],"of":[12,37,93,165,213,259,280],"hate":[13,81,143,214,230],"speech":[14,82,144,231],"has":[15],"accelerated,":[16],"inflicting":[17],"serious":[18],"harm":[19],"on":[20,53,111,141,202,267],"individuals,":[21],"communities,":[22],"society":[24],"as":[25,43,176,240],"a":[26,199,207],"whole.":[27],"Addressing":[28],"this":[29,100],"challenge":[30],"is":[31,75,87],"further":[32],"complicated":[33],"by":[34],"limitations":[36],"traditional":[38,236],"text":[39,106],"data":[40,107,184],"augmentation":[41,108,237,281,284],"techniques\u2014such":[42],"adding":[44],"noise":[45],"to":[46,60,70,187,276],"original":[48,127],"text,":[49],"substituting":[50],"words":[51],"based":[52,110],"context,":[54],"or":[55,242],"rephrasing":[56],"sentences\u2014which":[57],"often":[58],"fail":[59],"introduce":[61],"new":[62,71],"perspectives":[63],"that":[64,124],"could":[65],"help":[66],"classifiers":[67],"generalize":[68],"better":[69],"instances.":[72],"This":[73],"limitation":[74],"especially":[76],"critical":[77],"in":[78,134,155,262],"fields":[79],"like":[80],"detection,":[83],"where":[84],"creating":[85],"datasets":[86],"highly":[88],"labor-intensive,":[89],"involving":[90],"collection":[92],"positive":[94],"samples":[95,123],"expert":[97],"labeling.":[98],"In":[99],"work,":[101],"we":[102,146],"present":[103],"an":[104,228,256],"automatic":[105],"method":[109,139,175],"large":[112],"language":[113],"models":[114],"(LLMs)":[115],"using":[116],"demonstration-based":[117],"generation.":[118],"Our":[119,193],"approach":[120],"generates":[121],"diverse":[122,208],"maintain":[125],"writing":[128],"style,":[129],"effectively":[130],"bridging":[131],"semantic":[132],"gaps":[133],"data.":[136],"While":[137],"our":[138,174],"focuses":[140],"low-resource":[142,263],"datasets,":[145],"have":[147],"empirically":[148],"demonstrated":[149],"its":[150],"potential":[151],"consistency":[153],"even":[154],"larger":[156],"robust":[159],"dataset":[160,200,209],"scenarios.":[161],"The":[162],"careful":[163],"design":[164],"prompt,":[167],"combined":[168],"with":[169,246],"token":[170],"sampling":[171],"strategies,":[172],"positions":[173],"most":[178],"consistent":[179],"alternative":[180,283],"for":[181],"LLM-based":[182,251],"synthetic":[183],"generation":[185],"compared":[186,275],"existing":[188],"state-of-the-art":[189],"methods":[190,238],"prompts.":[192],"benchmarking":[194],"includes":[195],"(1)":[196],"CMSB":[197],",":[198,206,218,227],"centered":[201],"sexism;":[203],"(2)":[204],"ETHOS":[205],"encompassing":[210],"multiple":[211],"forms":[212],"speech;":[215],"(3)":[216],"Stormfront":[217],"which":[219],"contains":[220],"white":[221],"supremacist":[222],"discourse;":[223],"(4)":[225],"Antiasian":[226],"anti-Asian":[229],"dataset.":[232],"We":[233,253],"outperform":[234],"other":[235],"such":[239],"NLPAug":[241],"BackTranslation":[243],"benchmark":[245],"promising":[247],"results":[248],"against":[249],"another":[250],"techniques.":[252],"consistently":[254],"achieve":[255],"F1-score":[257],"improvement":[258],"approximately":[260],"4\u20136%":[261],"scenarios":[264],"1\u20132%":[266],"full":[268],"datasets.":[269],"These":[270],"gains":[271],"are":[272],"notably":[273],"higher":[274],"both":[277],"absence":[279],"methods.":[285]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}