{"id":"https://openalex.org/W7140104853","doi":"https://doi.org/10.18653/v1/2026.silkroadnlp-1.1","title":"Unmasking the Factual-Conceptual Gap in Persian Language Models","display_name":"Unmasking the Factual-Conceptual Gap in Persian Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140104853","doi":"https://doi.org/10.18653/v1/2026.silkroadnlp-1.1"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.silkroadnlp-1.1","doi":"https://doi.org/10.18653/v1/2026.silkroadnlp-1.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.silkroadnlp-1.1","pdf_url":"https://aclanthology.org/2026.silkroadnlp-1.1.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":"The Proceedings of the First Workshop on NLP and LLMs for the Iranian Language Family","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.silkroadnlp-1.1.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093367716","display_name":"Alireza Sakhaeirad","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Alireza Sakhaeirad","raw_affiliation_strings":["EPFL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EPFL","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120863860","display_name":"Ali Mamanpoosh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I39268498","display_name":"University of Isfahan","ror":"https://ror.org/05h9t7759","country_code":"IR","type":"education","lineage":["https://openalex.org/I39268498"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Ali Ma'manpoosh","raw_affiliation_strings":["University of Isfahan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Isfahan","institution_ids":["https://openalex.org/I39268498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5114654064","display_name":"Arshia Hemmat","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Arshia Hemmat","raw_affiliation_strings":["University of Oxford"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Oxford","institution_ids":["https://openalex.org/I40120149"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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":0.14519166,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.8901000022888184,"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":0.8901000022888184,"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":0.0723000019788742,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.005799999926239252,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/cultural-competence","display_name":"cultural competence","score":0.5350000262260437},{"id":"https://openalex.org/keywords/acquiescence-bias","display_name":"acquiescence bias","score":0.8379999995231628},{"id":"https://openalex.org/keywords/benchmark-design","display_name":"benchmark design","score":0.5009999871253967},{"id":"https://openalex.org/keywords/llm-evaluation","display_name":"LLM evaluation","score":0.40700000524520874}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6503999829292297},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.4309000074863434},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.42419999837875366},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4212000072002411},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.359499990940094},{"id":"https://openalex.org/C2776527531","wikidata":"https://www.wikidata.org/wiki/Q9168","display_name":"Persian","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C2778137410","wikidata":"https://www.wikidata.org/wiki/Q2732820","display_name":"Government (linguistics)","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.2669999897480011},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2418999969959259}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.silkroadnlp-1.1","doi":"https://doi.org/10.18653/v1/2026.silkroadnlp-1.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.silkroadnlp-1.1","pdf_url":"https://aclanthology.org/2026.silkroadnlp-1.1.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":"The Proceedings of the First Workshop on NLP and LLMs for the Iranian Language Family","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.silkroadnlp-1.1","doi":"https://doi.org/10.18653/v1/2026.silkroadnlp-1.1","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.silkroadnlp-1.1","pdf_url":"https://aclanthology.org/2026.silkroadnlp-1.1.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":"The Proceedings of the First Workshop on NLP and LLMs for the Iranian Language Family","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140104853.pdf","grobid_xml":"https://content.openalex.org/works/W7140104853.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7133235419","https://openalex.org/W7131832579","https://openalex.org/W4416247209","https://openalex.org/W6948587331","https://openalex.org/W7127418374","https://openalex.org/W7126278610","https://openalex.org/W4416037082","https://openalex.org/W4414790523","https://openalex.org/W4411119161","https://openalex.org/W4416034369"],"abstract_inverted_index":{"While":[0],"emerging":[1],"Persian":[2,62,86],"NLP":[3],"benchmarks":[4],"have":[5],"expanded":[6],"into":[7],"pragmatics":[8],"and":[9,18,35,56,64,103,115],"politeness,":[10],"they":[11],"rarely":[12],"distinguish":[13],"between":[14,111],"memorized":[15],"cultural":[16,123,137],"facts":[17],"the":[19,97,141],"ability":[20,99],"to":[21,81,100,135],"reason":[22],"about":[23],"implicit":[24],"social":[25],"norms.We":[26],"introduce":[27],"DIVANBENCH,":[28],"a":[29,107],"diagnostic":[30],"benchmark":[31],"focused":[32],"on":[33],"superstitions":[34],"customs,":[36],"arbitrary,":[37],"context-dependent":[38],"rules":[39],"that":[40,122],"resist":[41],"simple":[42],"logical":[43],"deduction.Through":[44],"315":[45],"questions":[46],"across":[47],"three":[48,66],"task":[49],"types":[50],"(factual":[51],"retrieval,":[52],"paired":[53],"scenario":[54],"verification,":[55],"situational":[57],"reasoning),":[58],"we":[59],"evaluate":[60],"seven":[61],"LLMs":[63],"reveal":[65],"critical":[67],"failures:":[68],"most":[69],"models":[70,105,133],"exhibit":[71],"severe":[72],"acquiescence":[73],"bias,":[74],"correctly":[75],"identifying":[76],"appropriate":[77],"behaviors":[78],"but":[79],"failing":[80],"reject":[82],"clear":[83],"violations;":[84],"continuous":[85],"pretraining":[87],"amplifies":[88],"this":[89],"bias":[90],"rather":[91],"than":[92,127],"improving":[93],"reasoning,":[94],"often":[95],"degrading":[96],"model's":[98],"discern":[101],"contradictions;":[102],"all":[104],"show":[106],"21%":[108],"performance":[109],"gap":[110],"retrieving":[112],"factual":[113],"knowledge":[114],"applying":[116],"it":[117],"in":[118],"scenarios.These":[119],"findings":[120],"demonstrate":[121],"competence":[124],"requires":[125],"more":[126],"scaling":[128],"monolingual":[129],"data,":[130],"as":[131],"current":[132],"learn":[134],"mimic":[136],"patterns":[138],"without":[139],"internalizing":[140],"underlying":[142],"schemas.":[143]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-24T00:00:00"}