{"id":"https://openalex.org/W7166806024","doi":"https://doi.org/10.18653/v1/2026.semeval-1.438","title":"GUIR at SemEval-2026 Task 7: Probing Cultural Knowledge in LLMs via Multi-Agent Debate","display_name":"GUIR at SemEval-2026 Task 7: Probing Cultural Knowledge in LLMs via Multi-Agent Debate","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166806024","doi":"https://doi.org/10.18653/v1/2026.semeval-1.438"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.semeval-1.438","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.semeval-1.438","pdf_url":"https://aclanthology.org/2026.semeval-1.438.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 20th International Workshop on Semantic Evaluation (2026)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.semeval-1.438.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116335556","display_name":"Reihaneh Iranmanesh","orcid":null},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Reihaneh Iranmanesh","raw_affiliation_strings":["Information Retrieval Lab Department of Computer Science Georgetown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Retrieval Lab Department of Computer Science Georgetown University","institution_ids":["https://openalex.org/I184565670"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139839673","display_name":"Ophir Frieder","orcid":null},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ophir Frieder","raw_affiliation_strings":["Information Retrieval Lab Department of Computer Science Georgetown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Retrieval Lab Department of Computer Science Georgetown University","institution_ids":["https://openalex.org/I184565670"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036610566","display_name":"Nazli Goharian","orcid":null},"institutions":[{"id":"https://openalex.org/I184565670","display_name":"Georgetown University","ror":"https://ror.org/05vzafd60","country_code":"US","type":"education","lineage":["https://openalex.org/I184565670"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nazli Goharian","raw_affiliation_strings":["Information Retrieval Lab Department of Computer Science Georgetown University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Retrieval Lab Department of Computer Science Georgetown University","institution_ids":["https://openalex.org/I184565670"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I184565670"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.77023647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3549","last_page":"3561"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.29510000348091125,"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/T10028","display_name":"Topic Modeling","score":0.29510000348091125,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.22759999334812164,"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/T12090","display_name":"Language and cultural evolution","score":0.10790000110864639,"subfield":{"id":"https://openalex.org/subfields/3316","display_name":"Cultural Studies"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6067000031471252},{"id":"https://openalex.org/keywords/cultural-knowledge","display_name":"Cultural knowledge","score":0.3102000057697296},{"id":"https://openalex.org/keywords/ethnic-group","display_name":"Ethnic group","score":0.2874000072479248},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.27250000834465027},{"id":"https://openalex.org/keywords/cultural-diversity","display_name":"Cultural diversity","score":0.27219998836517334},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.25619998574256897}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6067000031471252},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.40049999952316284},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.3961000144481659},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.36719998717308044},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3449000120162964},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.3416000008583069},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.3368000090122223},{"id":"https://openalex.org/C2994055011","wikidata":"https://www.wikidata.org/wiki/Q210272","display_name":"Cultural knowledge","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C137403100","wikidata":"https://www.wikidata.org/wiki/Q41710","display_name":"Ethnic group","level":2,"score":0.2874000072479248},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.27250000834465027},{"id":"https://openalex.org/C125209646","wikidata":"https://www.wikidata.org/wiki/Q1338878","display_name":"Cultural diversity","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.27090001106262207},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C514011633","wikidata":"https://www.wikidata.org/wiki/Q1428168","display_name":"Traditional knowledge","level":3,"score":0.25619998574256897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.semeval-1.438","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.semeval-1.438","pdf_url":"https://aclanthology.org/2026.semeval-1.438.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 20th International Workshop on Semantic Evaluation (2026)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.semeval-1.438","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.semeval-1.438","pdf_url":"https://aclanthology.org/2026.semeval-1.438.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 20th International Workshop on Semantic Evaluation (2026)","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4539489150047302}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166806024.pdf","grobid_xml":"https://content.openalex.org/works/W7166806024.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0],"present":[1],"the":[2,18,39,42,59,115,125,141,148,152],"GUIR":[3],"system":[4,33,142],"for":[5,154],"SemEval-2026":[6],"Task":[7],"7,":[8],"Everyday":[9],"Knowledge":[10],"Across":[11],"Diverse":[12],"Languages":[13],"and":[14,83,95],"Cultures,":[15],"which":[16,21,90],"probes":[17],"extent":[19],"to":[20,79],"general-purpose":[22],"LLMs":[23],"encode":[24],"cultural":[25],"knowledge":[26],"without":[27],"any":[28],"culturespecific":[29],"supervision":[30],"or":[31],"fine-tuning.Our":[32],"addresses":[34],"two":[35],"tracks":[36],"built":[37],"on":[38,114,124],"BLEND":[40],"benchmark.For":[41],"short-answer":[43],"question":[44,61],"(SAQ)":[45],"track,":[46,63],"we":[47,64],"employ":[48],"zero-shot":[49,70],"prompting":[50],"with":[51,73,137],"gpt-4.1,achieving":[52],"55.5%":[53],"accuracy":[54,104],"across":[55,105],"61":[56],"language":[57],"locales.For":[58],"multiplechoice":[60],"(MCQ)":[62],"propose":[65],"a":[66,85,120],"three-stage":[67],"pipeline:":[68],"(1)":[69],"chain-ofthought":[71],"inference":[72],"gpt-5-mini,":[74],"(2)":[75],"crosslocale":[76],"majority":[77],"voting":[78],"correct":[80],"inconsistent":[81],"predictions,":[82],"(3)":[84],"multi-agent":[86],"debate":[87],"protocol":[88],"in":[89],"three":[91],"LLM":[92],"instances":[93],"argue":[94],"adjudicate":[96],"over":[97],"residual":[98],"errors.This":[99],"pipeline":[100],"achieves":[101],"97.47%":[102],"overall":[103],"30":[106],"locales,":[107],"ranking":[108],"first":[109],"among":[110],"all":[111],"submitted":[112],"systems":[113],"MCQ":[116],"track.We":[117],"further":[118],"conduct":[119],"targeted":[121],"human":[122,138],"evaluation":[123,156],"Persian":[126],"locale,":[127],"revealing":[128],"that":[129],"BLEnD's":[130],"lemmamatching":[131],"scorer":[132],"systematically":[133],"underestimates":[134],"model":[135],"performance,":[136],"annotators":[139],"scoring":[140],"18":[143],"percentage":[144],"points":[145],"higher":[146],"than":[147],"lemma-matching":[149],"evaluation.This":[150],"reveals":[151],"need":[153],"better":[155],"of":[157],"morphologically":[158],"rich":[159],"languages":[160],"like":[161],"Persian.":[162]},"counts_by_year":[],"updated_date":"2026-08-24T07:32:12.397491","created_date":"2026-07-02T00:00:00"}