{"id":"https://openalex.org/W7137870810","doi":"https://doi.org/10.1609/aaai.v40i1.37040","title":"Benchmarking LLMs for Political Science: A United Nations Perspective","display_name":"Benchmarking LLMs for Political Science: A United Nations Perspective","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7137870810","doi":"https://doi.org/10.1609/aaai.v40i1.37040"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i1.37040","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.37040","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37040/41002","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37040/41002","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129658378","display_name":"Yueqing Liang","orcid":null},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yueqing Liang","raw_affiliation_strings":["Illinois Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129684915","display_name":"Liangwei Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Liangwei Yang","raw_affiliation_strings":["Salesforce Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce Research","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129672800","display_name":"Chen Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I39422238","display_name":"University of Illinois Chicago","ror":"https://ror.org/02mpq6x41","country_code":"US","type":"education","lineage":["https://openalex.org/I39422238"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chen Wang","raw_affiliation_strings":["University of Illinois Chicago"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Chicago","institution_ids":["https://openalex.org/I39422238"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015122283","display_name":"Congying Xia","orcid":"https://orcid.org/0000-0001-7581-0882"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Congying Xia","raw_affiliation_strings":["Meta GenAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meta GenAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129692139","display_name":"Rui Meng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210155268","display_name":"Salesforce (United States)","ror":"https://ror.org/057315g56","country_code":"US","type":"company","lineage":["https://openalex.org/I4210155268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rui Meng","raw_affiliation_strings":["Salesforce Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Salesforce Research","institution_ids":["https://openalex.org/I4210155268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048359121","display_name":"Xiongxiao Xu","orcid":"https://orcid.org/0000-0003-2097-5246"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiongxiao Xu","raw_affiliation_strings":["Illinois Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129738882","display_name":"Haoran Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haoran Wang","raw_affiliation_strings":["Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University","institution_ids":["https://openalex.org/I150468666"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129693663","display_name":"Ali Payani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ali Payani","raw_affiliation_strings":["Cisco Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cisco Research","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129711308","display_name":"Kai Shu","orcid":null},"institutions":[{"id":"https://openalex.org/I150468666","display_name":"Emory University","ror":"https://ror.org/03czfpz43","country_code":"US","type":"education","lineage":["https://openalex.org/I150468666"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Shu","raw_affiliation_strings":["Emory University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Emory University","institution_ids":["https://openalex.org/I150468666"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"1","first_page":"738","last_page":"745"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.8636000156402588,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.8636000156402588,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11147","display_name":"Misinformation and Its Impacts","score":0.013700000010430813,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.005400000140070915,"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/politics","display_name":"Politics","score":0.6887000203132629},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6284000277519226},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.5741999745368958},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4499000012874603},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.40529999136924744},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.3061000108718872}],"concepts":[{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.6887000203132629},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6284000277519226},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.5741999745368958},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.503000020980835},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4499000012874603},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.40529999136924744},{"id":"https://openalex.org/C3116431","wikidata":"https://www.wikidata.org/wiki/Q31728","display_name":"Public administration","level":1,"score":0.39169999957084656},{"id":"https://openalex.org/C138921699","wikidata":"https://www.wikidata.org/wiki/Q47555","display_name":"Political economy","level":1,"score":0.3695000112056732},{"id":"https://openalex.org/C50522688","wikidata":"https://www.wikidata.org/wiki/Q189833","display_name":"Economic growth","level":1,"score":0.3142000138759613},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.3061000108718872},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C47768531","wikidata":"https://www.wikidata.org/wiki/Q1127188","display_name":"Development economics","level":1,"score":0.29840001463890076},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.26600000262260437},{"id":"https://openalex.org/C152192407","wikidata":"https://www.wikidata.org/wiki/Q1147507","display_name":"Political history","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C528167355","wikidata":"https://www.wikidata.org/wiki/Q258307","display_name":"National security","level":2,"score":0.2596000134944916}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i1.37040","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.37040","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37040/41002","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i1.37040","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i1.37040","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/37040/41002","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7295828461647034,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7137870810.pdf","grobid_xml":"https://content.openalex.org/works/W7137870810.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large":[0],"Language":[1],"Models":[2],"(LLMs)":[3],"have":[4,51],"achieved":[5],"significant":[6],"advances":[7],"in":[8,151,161,179],"natural":[9],"language":[10],"processing,":[11],"yet":[12],"their":[13,157],"potential":[14,145],"for":[15],"high-stake":[16],"political":[17,48,100,138,162,190],"decision-making":[18,39,124],"remains":[19],"largely":[20],"unexplored.":[21],"This":[22],"paper":[23],"addresses":[24],"the":[25,30,35,42,84,89,118,122,144,165,172,184],"gap":[26],"by":[27],"focusing":[28],"on":[29],"application":[31],"of":[32,121,148,167,187],"LLMs":[33,96,150,178],"to":[34,69,94,130,134,175,183],"United":[36,85],"Nations":[37,86],"(UN)":[38],"process,":[40],"where":[41],"stakes":[43],"are":[44],"particularly":[45],"high":[46],"and":[47,76,111,127,136,146,159,189],"decisions":[49],"can":[50],"far-reaching":[52],"consequences.":[53],"We":[54],"introduce":[55],"a":[56],"novel":[57],"dataset":[58],"comprising":[59],"publicly":[60],"available":[61],"UN":[62,123,180],"Security":[63],"Council":[64],"(UNSC)":[65],"records":[66],"from":[67],"1994":[68],"2024,":[70],"including":[71],"draft":[72,108],"resolutions,":[73],"voting":[74,106],"records,":[75],"diplomatic":[77],"speeches.":[78],"Using":[79],"this":[80,152,170],"dataset,":[81],"we":[82],"propose":[83],"Benchmark":[87],"(UNBench),":[88],"first":[90,173],"comprehensive":[91],"benchmark":[92,174],"designed":[93],"evaluate":[95,177],"across":[97],"four":[98],"interconnected":[99],"science":[101],"tasks:":[102],"co-penholder":[103],"judgment,":[104],"representative":[105,112],"simulation,":[107],"adoption":[109],"prediction,":[110],"statement":[113],"generation.":[114],"These":[115],"tasks":[116],"span":[117],"three":[119],"stages":[120],"process\u2014drafting,":[125],"voting,":[126],"discussing\u2014and":[128],"aim":[129],"assess":[131],"LLMs'":[132],"ability":[133],"understand":[135],"simulate":[137],"dynamics.":[139],"Our":[140],"experimental":[141],"analysis":[142],"demonstrates":[143],"challenges":[147],"applying":[149],"domain,":[153],"providing":[154],"insights":[155],"into":[156],"strengths":[158],"limitations":[160],"science.":[163,191],"To":[164],"best":[166],"our":[168],"knowledge,":[169],"is":[171],"systematically":[176],"decision-making,":[181],"contributing":[182],"growing":[185],"intersection":[186],"AI":[188]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-03-18T00:00:00"}
