{"id":"https://openalex.org/W7160065811","doi":"https://doi.org/10.63317/3dhy55mxo9zb","title":"LLMs as Annotators: Evaluating Model\u2013Human Alignment in Detecting Contentious Language in Historical Corpora","display_name":"LLMs as Annotators: Evaluating Model\u2013Human Alignment in Detecting Contentious Language in Historical Corpora","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W7160065811","doi":"https://doi.org/10.63317/3dhy55mxo9zb"},"language":"en","primary_location":{"id":"doi:10.63317/3dhy55mxo9zb","is_oa":false,"landing_page_url":"https://doi.org/10.63317/3dhy55mxo9zb","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":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ir.cwi.nl/pub/36414/36414.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135139205","display_name":"Yahui Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yahui Zhao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135258313","display_name":"Clemencia Siro","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Clemencia Siro","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135258769","display_name":"Laura Hollink","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Laura Hollink","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":0.4327854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"10883","last_page":"10896"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.2231999933719635,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.2231999933719635,"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/T12380","display_name":"Authorship Attribution and Profiling","score":0.20980000495910645,"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":0.17249999940395355,"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/corpus-linguistics","display_name":"Corpus linguistics","score":0.3562000095844269},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.29750001430511475},{"id":"https://openalex.org/keywords/computational-linguistics","display_name":"Computational linguistics","score":0.27959999442100525},{"id":"https://openalex.org/keywords/contentious-politics","display_name":"Contentious politics","score":0.2671000063419342}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5665000081062317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5116000175476074},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4878999888896942},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42500001192092896},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.40540000796318054},{"id":"https://openalex.org/C532629269","wikidata":"https://www.wikidata.org/wiki/Q865083","display_name":"Corpus linguistics","level":2,"score":0.3562000095844269},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.3188000023365021},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.29750001430511475},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C2778814104","wikidata":"https://www.wikidata.org/wiki/Q5165105","display_name":"Contentious politics","level":4,"score":0.2671000063419342},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.25850000977516174}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.63317/3dhy55mxo9zb","is_oa":false,"landing_page_url":"https://doi.org/10.63317/3dhy55mxo9zb","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:cwi.nl:36414","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/36414","pdf_url":"https://ir.cwi.nl/pub/36414/36414.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:cwi.nl:36414","is_oa":true,"landing_page_url":"https://ir.cwi.nl/pub/36414","pdf_url":"https://ir.cwi.nl/pub/36414/36414.pdf","source":{"id":"https://openalex.org/S7407055335","display_name":"Centrum Wiskunde & Informatica (CWI), the national research institute for mathematics and computer science in the Netherlands","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7160065811.pdf","grobid_xml":"https://content.openalex.org/works/W7160065811.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Historical":[0],"texts":[1],"often":[2],"contain":[3],"terminology":[4],"that":[5,111,138,152],"reflects":[6],"outdated":[7],"or":[8,101,132],"harmful":[9,115],"social":[10],"values.":[11],"Identifying":[12],"such":[13],"contentious":[14],"terms":[15,65,126],"is":[16,34,104],"essential":[17],"for":[18,122,129,145],"the":[19,62,72],"Galleries,":[20],"Libraries,":[21],"Archives,":[22],"and":[23,33,78,86,124,127,155],"Museums":[24],"(GLAM)":[25],"community,":[26],"but":[27,97],"manual":[28],"annotation":[29,161],"requires":[30],"cultural":[31],"expertise":[32],"difficult":[35],"to":[36,119,160],"scale.":[37],"This":[38],"study":[39],"evaluates":[40],"whether":[41],"large":[42],"language":[43],"models":[44,90],"(LLMs)":[45],"can":[46,140],"support":[47],"this":[48],"process":[49],"by":[50],"aligning":[51],"with":[52],"human":[53,153],"judgments":[54],"of":[55,107],"contentiousness":[56,121],"in":[57,66,148],"historical":[58,102,149],"Dutch":[59,63],"corpora.":[60],"Using":[61],"Contentious":[64],"Contexts":[67],"Corpus":[68],"(ConConCor),":[69],"we":[70],"formalize":[71],"task":[73],"as":[74,142],"context-dependent":[75],"binary":[76],"classification":[77],"compare":[79],"two":[80],"LLMs":[81,112,139],"across":[82],"multiple":[83],"prompt":[84],"configurations":[85],"evaluation":[87],"scenarios.":[88],"The":[89],"achieve":[91],"near-human-level":[92],"agreement":[93],"on":[94],"explicit":[95],"cases":[96],"diverge":[98],"when":[99],"contextual":[100,156],"reasoning":[103],"required.":[105],"Analysis":[106],"disagreement":[108],"patterns":[109],"shows":[110],"capture":[113],"overtly":[114],"expressions":[116],"yet":[117],"tend":[118],"over-predict":[120],"identity-related":[123],"colonial":[125],"under-predict":[128],"semantically":[130],"shifted":[131],"figurative":[133],"uses.":[134],"These":[135],"findings":[136],"suggest":[137],"serve":[141],"auxiliary":[143],"annotators":[144],"sensitive-language":[146],"detection":[147],"materials,":[150],"provided":[151],"oversight":[154],"interpretation":[157],"remain":[158],"central":[159],"workflows.":[162]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-05T00:00:00"}
