{"id":"https://openalex.org/W7104364214","doi":"https://doi.org/10.18653/v1/2025.nlperspectives-1.9","title":"Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication","display_name":"Aligning NLP Models with Target Population Perspectives using PAIR: Population-Aligned Instance Replication","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7104364214","doi":"https://doi.org/10.18653/v1/2025.nlperspectives-1.9"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.nlperspectives-1.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.nlperspectives-1.9","pdf_url":"https://aclanthology.org/2025.nlperspectives-1.9.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":"Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.nlperspectives-1.9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Stephanie Eckman","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stephanie Eckman","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Bolei Ma","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bolei Ma","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Christoph Kern","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Christoph Kern","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Rob Chew","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rob Chew","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Barbara Plank","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barbara Plank","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Frauke Kreuter","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Frauke Kreuter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.91186826,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"100","last_page":"110"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12262","display_name":"Hate Speech and Cyberbullying Detection","score":0.8248000144958496,"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":0.8248000144958496,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.03959999978542328,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.03229999914765358,"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/population","display_name":"Population","score":0.6664000153541565},{"id":"https://openalex.org/keywords/offensive","display_name":"Offensive","score":0.6047000288963318},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.5936999917030334},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5748000144958496},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4099999964237213},{"id":"https://openalex.org/keywords/replication","display_name":"Replication (statistics)","score":0.40549999475479126}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7642999887466431},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6809999942779541},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.6664000153541565},{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.6047000288963318},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5975000262260437},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.5936999917030334},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5748000144958496},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49230000376701355},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C12590798","wikidata":"https://www.wikidata.org/wiki/Q3933199","display_name":"Replication (statistics)","level":2,"score":0.40549999475479126},{"id":"https://openalex.org/C155092808","wikidata":"https://www.wikidata.org/wiki/Q182557","display_name":"Computational linguistics","level":2,"score":0.36149999499320984},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C111219384","wikidata":"https://www.wikidata.org/wiki/Q6954384","display_name":"NIST","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.2939000129699707},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2612000107765198}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.nlperspectives-1.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.nlperspectives-1.9","pdf_url":"https://aclanthology.org/2025.nlperspectives-1.9.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":"Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP","raw_type":"proceedings-article"},{"id":"pmh:oai:epub.ub.uni-muenchen.de:129504","is_oa":true,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bvb:19-epub-129504-6","pdf_url":"https://epub.ub.uni-muenchen.de/129504/1/10.1515_9783110761139-fm.pdf","source":{"id":"https://openalex.org/S4306401845","display_name":"Open access LMU (Ludwid Maxmilian's Universitat Munchen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:epub.ub.uni-muenchen.de:130361","is_oa":true,"landing_page_url":"http://nbn-resolving.de/urn:nbn:de:bvb:19-epub-130361-2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401845","display_name":"Open access LMU (Ludwid Maxmilian's Universitat Munchen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I8204097","host_organization_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","host_organization_lineage":["https://openalex.org/I8204097"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.nlperspectives-1.9","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.nlperspectives-1.9","pdf_url":"https://aclanthology.org/2025.nlperspectives-1.9.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":"Proceedings of the The 4th Workshop on Perspectivist Approaches to NLP","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310334","display_name":"RTI International","ror":"https://ror.org/052tfza37"},{"id":"https://openalex.org/F4320323390","display_name":"Ludwig-Maximilians-Universit\u00e4t M\u00fcnchen","ror":"https://ror.org/05591te55"},{"id":"https://openalex.org/F4320324159","display_name":"Universit\u00e4t Mannheim","ror":"https://ror.org/031bsb921"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W7104364214.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Models":[0],"trained":[1],"on":[2,51],"crowdsourced":[3],"annotations":[4,82],"may":[5],"not":[6,17],"reflect":[7,40],"population":[8,42,89],"views,":[9],"if":[10],"those":[11],"who":[12],"work":[13],"as":[14],"annotators":[15],"do":[16],"represent":[18],"the":[19,97],"broader":[20],"population.":[21],"In":[22],"this":[23],"paper,":[24],"we":[25,62],"propose":[26],"PAIR:":[27],"Population-Aligned":[28],"Instance":[29],"Replication,":[30],"a":[31],"post-processing":[32],"method":[33],"that":[34,64],"adjusts":[35],"training":[36,100],"data":[37,101],"to":[38,87],"better":[39],"target":[41],"characteristics":[43],"without":[44],"collecting":[45],"additional":[46],"annotations.":[47],"Using":[48],"simulation":[49],"studies":[50],"offensive":[52],"language":[53],"and":[54,102],"hate":[55],"speech":[56],"detection":[57],"with":[58,93],"varying":[59],"annotator":[60,85],"compositions,":[61],"show":[63],"non-representative":[65],"pools":[66],"degrade":[67],"model":[68,103],"calibration":[69,78],"while":[70],"leaving":[71],"accuracy":[72],"largely":[73],"unchanged.":[74],"PAIR":[75],"corrects":[76],"these":[77],"problems":[79],"by":[80],"replicating":[81],"from":[83],"underrepresented":[84],"groups":[86],"match":[88],"proportions.":[90],"We":[91],"conclude":[92],"recommendations":[94],"for":[95],"improving":[96],"representativity":[98],"of":[99],"performance.":[104]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-11-08T00:00:00"}