{"id":"https://openalex.org/W4405766544","doi":"https://doi.org/10.63317/2uppkbro3uvq","title":"SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs","display_name":"SubData: Bridging Heterogeneous Datasets to Enable Theory-Driven Evaluation of Political and Demographic Perspectives in LLMs","publication_year":2026,"publication_date":"2026-05-01","ids":{"openalex":"https://openalex.org/W4405766544","doi":"https://doi.org/10.63317/2uppkbro3uvq"},"language":"en","primary_location":{"id":"doi:10.63317/2uppkbro3uvq","is_oa":true,"landing_page_url":"https://doi.org/10.63317/2uppkbro3uvq","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nlperspectives/pdf/2026.nlperspectives-1.9.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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":"gold","oa_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nlperspectives/pdf/2026.nlperspectives-1.9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114601870","display_name":"Pietro Bernardelle","orcid":null},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Pietro Bernardelle","raw_affiliation_strings":["The University of Queensland , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland , Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068460217","display_name":"Leon Fr\u00f6hling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Leon Froehling","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Stefano Civelli","orcid":null},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Stefano Civelli","raw_affiliation_strings":["The University of Queensland , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland , Australia","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052565959","display_name":"Gianluca Demartini","orcid":"https://orcid.org/0000-0002-7311-3693"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Gianluca Demartini","raw_affiliation_strings":["The University of Queensland , Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Queensland , Australia","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.00477062,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"84","last_page":"97"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8377000093460083,"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":0.8377000093460083,"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/python","display_name":"Python (programming language)","score":0.9407849907875061},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.8185667991638184},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7065284848213196},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.4618929624557495},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.3553745746612549},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.34184208512306213},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.33020371198654175},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32882487773895264},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11922293901443481},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.06726756691932678}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.9407849907875061},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.8185667991638184},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7065284848213196},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.4618929624557495},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.3553745746612549},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.34184208512306213},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.33020371198654175},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32882487773895264},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11922293901443481},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.06726756691932678}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/2uppkbro3uvq","is_oa":true,"landing_page_url":"https://doi.org/10.63317/2uppkbro3uvq","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nlperspectives/pdf/2026.nlperspectives-1.9.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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:2412.16783","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2412.16783","pdf_url":"https://arxiv.org/pdf/2412.16783","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","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2412.16783","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.16783","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.63317/2uppkbro3uvq","is_oa":true,"landing_page_url":"https://doi.org/10.63317/2uppkbro3uvq","pdf_url":"http://www.lrec-conf.org/proceedings/lrec2026/workshops/nlperspectives/pdf/2026.nlperspectives-1.9.pdf","source":null,"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Language Resources and Evaluation Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405766544.pdf","grobid_xml":"https://content.openalex.org/works/W4405766544.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2341492732","https://openalex.org/W3187193180","https://openalex.org/W106542691","https://openalex.org/W1699080303","https://openalex.org/W4297799326","https://openalex.org/W3116064965","https://openalex.org/W4287027380","https://openalex.org/W3193760048","https://openalex.org/W2207495067","https://openalex.org/W1906486629"],"abstract_inverted_index":{"As":[0],"increasingly":[1],"capable":[2],"large":[3],"language":[4,147],"models":[5],"(LLMs)":[6],"emerge,":[7],"researchers":[8],"have":[9],"begun":[10],"exploring":[11],"their":[12],"potential":[13],"for":[14,71,111,140],"subjective":[15],"tasks.While":[16],"recent":[17],"work":[18],"demonstrates":[19],"that":[20],"LLMs":[21,77,93,142],"can":[22],"be":[23],"aligned":[24,95],"with":[25,96,123],"diverse":[26,112],"human":[27],"perspectives,":[28],"evaluating":[29,141],"this":[30,51,54,87],"alignment":[31,144],"on":[32,145],"downstream":[33],"tasks":[34],"(e.g.,":[35,94],"hate":[36],"speech":[37],"detection)":[38],"remains":[39],"challenging":[40],"due":[41],"to":[42,75,89,130],"the":[43],"use":[44],"of":[45],"inconsistent":[46],"datasets":[47,74],"across":[48],"studies.To":[49],"address":[50],"issue,":[52],"in":[53],"resource":[55],"paper":[56],"we":[57,62],"propose":[58],"a":[59,83,136],"two-step":[60],"framework:":[61],"(1)":[63],"introduce":[64],"SubData,":[65],"an":[66,124],"open-source":[67],"Python":[68],"library":[69,88],"designed":[70],"standardizing":[72],"heterogeneous":[73],"evaluate":[76],"perspective":[78,143],"alignment;":[79],"and":[80,107,127],"(2)":[81],"present":[82],"theory-driven":[84],"approach":[85],"leveraging":[86],"test":[90],"how":[91],"differently-aligned":[92],"different":[97],"political":[98],"viewpoints)":[99],"classify":[100],"content":[101],"targeting":[102],"specific":[103],"demographics.SubData's":[104],"flexible":[105],"mapping":[106],"taxonomy":[108],"enable":[109],"customization":[110],"research":[113],"needs,":[114],"distinguishing":[115],"it":[116],"from":[117],"existing":[118],"resources.We":[119],"illustrate":[120],"its":[121],"usage":[122],"example":[125],"application":[126],"invite":[128],"contributions":[129],"extend":[131],"our":[132],"initial":[133],"release":[134],"into":[135],"multi-construct":[137],"benchmark":[138],"suite":[139],"natural":[146],"processing":[148],"tasks.":[149]},"counts_by_year":[],"updated_date":"2026-08-23T07:36:19.812096","created_date":"2024-12-25T00:00:00"}