{"id":"https://openalex.org/W4417292207","doi":"https://doi.org/10.63317/22n5hekovvrz","title":"Can LLMs Evaluate What They Cannot Annotate? Revisiting LLM Reliability in Hate Speech Detection","display_name":"Can LLMs Evaluate What They Cannot Annotate? Revisiting LLM Reliability in Hate Speech Detection","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4417292207","doi":"https://doi.org/10.63317/22n5hekovvrz"},"language":null,"primary_location":{"id":"doi:10.63317/22n5hekovvrz","is_oa":false,"landing_page_url":"https://doi.org/10.63317/22n5hekovvrz","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2512.09662","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003367619","display_name":"P Piot","orcid":"https://orcid.org/0000-0002-7069-3389"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paloma Piot","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070408128","display_name":"David Otero","orcid":"https://orcid.org/0000-0003-1139-0449"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Otero","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034892295","display_name":"Patricia Mart\u00edn-Rodilla","orcid":"https://orcid.org/0000-0002-1540-883X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patricia Martin-Rodilla","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5046723532","display_name":"Javier Parapar","orcid":"https://orcid.org/0000-0002-5997-8252"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Javier Parapar","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":0.03653402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4358","last_page":"4370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.9916999936103821,"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":0.9916999936103821,"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/T10664","display_name":"Sentiment Analysis and Opinion Mining","score":0.001500000013038516,"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/T11644","display_name":"Spam and Phishing Detection","score":0.001500000013038516,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/proxy","display_name":"Proxy (statistics)","score":0.6251000165939331},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.609499990940094},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.558899998664856},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.5375000238418579},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.3982999920845032},{"id":"https://openalex.org/keywords/risk-assessment","display_name":"Risk assessment","score":0.3398999869823456},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.3156000077724457}],"concepts":[{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.6251000165939331},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.609499990940094},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5914999842643738},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.558899998664856},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5375000238418579},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.42410001158714294},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.3982999920845032},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3889000117778778},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38839998841285706},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37369999289512634},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3400999903678894},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.32179999351501465},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.2989000082015991},{"id":"https://openalex.org/C61863361","wikidata":"https://www.wikidata.org/wiki/Q470749","display_name":"Inter-rater reliability","level":3,"score":0.29670000076293945},{"id":"https://openalex.org/C169806903","wikidata":"https://www.wikidata.org/wiki/Q5937752","display_name":"Human error","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.26910001039505005},{"id":"https://openalex.org/C191147762","wikidata":"https://www.wikidata.org/wiki/Q186289","display_name":"Human reliability","level":3,"score":0.2621000111103058},{"id":"https://openalex.org/C96608239","wikidata":"https://www.wikidata.org/wiki/Q1199823","display_name":"Statistical power","level":2,"score":0.2606000006198883}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/22n5hekovvrz","is_oa":false,"landing_page_url":"https://doi.org/10.63317/22n5hekovvrz","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2512.09662","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.09662","pdf_url":"https://arxiv.org/pdf/2512.09662","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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"},{"id":"doi:10.48550/arxiv.2512.09662","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2512.09662","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2512.09662","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2512.09662","pdf_url":"https://arxiv.org/pdf/2512.09662","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"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":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417292207.pdf","grobid_xml":"https://content.openalex.org/works/W4417292207.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hate":[0],"speech":[1],"spreads":[2],"widely":[3],"online,":[4],"harming":[5],"individuals":[6],"and":[7,186],"communities,":[8],"making":[9],"automatic":[10],"detection":[11],"essential":[12],"for":[13,199,209],"large-scale":[14],"moderation,":[15],"yet":[16],"detecting":[17],"it":[18,52],"remains":[19],"difficult.":[20],"Part":[21],"of":[22,143],"the":[23,140,161,179],"challenge":[24],"lies":[25],"in":[26,80,211],"subjectivity:":[27],"what":[28],"one":[29],"person":[30],"flags":[31],"as":[32,38,45,53,154,192,205],"hate":[33],"speech,":[34],"another":[35],"may":[36],"see":[37],"benign.":[39],"Traditional":[40],"annotation":[41],"agreement":[42],"metrics,":[43],"such":[44],"Cohen's":[46],"$\u03ba$,":[47],"oversimplify":[48],"this":[49,84,109,133],"disagreement,":[50],"treating":[51],"an":[54,112],"error":[55],"rather":[56],"than":[57],"meaningful":[58],"diversity.":[59],"Meanwhile,":[60],"Large":[61],"Language":[62],"Models":[63],"(LLMs)":[64],"promise":[65],"scalable":[66,207],"annotation,":[67],"but":[68],"prior":[69],"studies":[70],"demonstrate":[71],"that":[72,98,116],"they":[73,182,202],"cannot":[74],"fully":[75],"replace":[76],"human":[77,129,148,158,200],"judgement,":[78],"especially":[79],"subjective":[81,212],"tasks.":[82,214],"In":[83],"work,":[85],"we":[86,114],"reexamine":[87],"LLM":[88],"reliability":[89],"using":[90],"a":[91,197,206],"subjectivity-aware":[92],"framework,":[93],"cross-Rater":[94],"Reliability":[95],"(xRR),":[96],"revealing":[97],"even":[99],"under":[100],"fairer":[101],"lens,":[102],"LLMs":[103,174],"still":[104],"diverge":[105],"from":[106,147,176],"humans.":[107],"Yet":[108],"limitation":[110],"opens":[111],"opportunity:":[113],"find":[115],"LLM-generated":[117,137,167],"annotations":[118,138],"can":[119],"reliably":[120],"reflect":[121],"performance":[122,145],"trends":[123],"across":[124],"classification":[125,187],"models,":[126],"correlating":[127],"with":[128,166],"evaluations.":[130],"We":[131],"test":[132],"by":[134,157],"examining":[135],"whether":[136,151],"preserve":[139,160],"relative":[141],"ordering":[142],"model":[144],"derived":[146],"evaluation":[149,210],"(i.e.":[150],"models":[152],"ranked":[153],"more":[155],"reliable":[156],"annotators":[159],"same":[162],"order":[163],"when":[164],"evaluated":[165],"labels).":[168],"Our":[169],"results":[170],"show":[171],"that,":[172],"although":[173],"differ":[175],"humans":[177],"at":[178],"instance":[180],"level,":[181],"reproduce":[183],"similar":[184],"ranking":[185],"patterns,":[188],"suggesting":[189],"their":[190],"potential":[191],"proxy":[193,208],"evaluators.":[194],"While":[195],"not":[196],"substitute":[198],"annotators,":[201],"might":[203],"serve":[204],"NLP":[213]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-12-12T00:00:00"}