{"id":"https://openalex.org/W4416247209","doi":"https://doi.org/10.63317/2ee2xn7cdmrr","title":"PBBQ: A Persian Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models","display_name":"PBBQ: A Persian Bias Benchmark Dataset Curated with Human-AI Collaboration for Large Language Models","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4416247209","doi":"https://doi.org/10.63317/2ee2xn7cdmrr"},"language":null,"primary_location":{"id":"doi:10.63317/2ee2xn7cdmrr","is_oa":false,"landing_page_url":"https://doi.org/10.63317/2ee2xn7cdmrr","pdf_url":null,"source":null,"license":null,"license_id":null,"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":"green","oa_url":"https://arxiv.org/pdf/2510.19616","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5094008588","display_name":"Farhan Farsi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farhan Farsi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094008589","display_name":"Shayan Bali","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shayan Bali","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120450341","display_name":"Fatemeh Valeh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fatemeh Valeh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120499395","display_name":"Parsa Ghofrani","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Parsa Ghofrani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120549474","display_name":"Alireza Pakniat","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alireza Pakniat","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114355092","display_name":"Kian Kashfipour","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Seyedkian Kashfipour","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5012596151","display_name":"Amir H. Payberah","orcid":"https://orcid.org/0000-0002-2748-8929"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Amir H. Payberah","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.0251938,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3944","last_page":"3960"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13910","display_name":"Computational and Text Analysis Methods","score":0.40049999952316284,"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":0.40049999952316284,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.041600000113248825,"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/T10028","display_name":"Topic Modeling","score":0.036400001496076584,"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/persian","display_name":"Persian","score":0.8152999877929688},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.682200014591217},{"id":"https://openalex.org/keywords/replicate","display_name":"Replicate","score":0.5870000123977661},{"id":"https://openalex.org/keywords/social-media","display_name":"Social media","score":0.4388999938964844},{"id":"https://openalex.org/keywords/cultural-bias","display_name":"Cultural bias","score":0.3102000057697296},{"id":"https://openalex.org/keywords/computational-sociology","display_name":"Computational sociology","score":0.3003000020980835}],"concepts":[{"id":"https://openalex.org/C2776527531","wikidata":"https://www.wikidata.org/wiki/Q9168","display_name":"Persian","level":2,"score":0.8152999877929688},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.682200014591217},{"id":"https://openalex.org/C2781162219","wikidata":"https://www.wikidata.org/wiki/Q26250693","display_name":"Replicate","level":2,"score":0.5870000123977661},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.5515999794006348},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5376999974250793},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4528999924659729},{"id":"https://openalex.org/C518677369","wikidata":"https://www.wikidata.org/wiki/Q202833","display_name":"Social media","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41429999470710754},{"id":"https://openalex.org/C37773902","wikidata":"https://www.wikidata.org/wiki/Q970594","display_name":"Cultural bias","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C126349790","wikidata":"https://www.wikidata.org/wiki/Q905036","display_name":"Computational sociology","level":2,"score":0.3003000020980835},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28619998693466187},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.2831999957561493},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.28189998865127563},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2786000072956085},{"id":"https://openalex.org/C131158328","wikidata":"https://www.wikidata.org/wiki/Q1307337","display_name":"Social influence","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.257099986076355},{"id":"https://openalex.org/C125209646","wikidata":"https://www.wikidata.org/wiki/Q1338878","display_name":"Cultural diversity","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/2ee2xn7cdmrr","is_oa":false,"landing_page_url":"https://doi.org/10.63317/2ee2xn7cdmrr","pdf_url":null,"source":null,"license":null,"license_id":null,"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:2510.19616","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.19616","pdf_url":"https://arxiv.org/pdf/2510.19616","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2510.19616","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.19616","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.19616","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.19616","pdf_url":"https://arxiv.org/pdf/2510.19616","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416247209.pdf","grobid_xml":"https://content.openalex.org/works/W4416247209.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,106,161,172],"increasing":[2],"adoption":[3],"of":[4,110,171],"large":[5],"language":[6,114],"models":[7,127],"(LLMs),":[8],"ensuring":[9],"their":[10],"alignment":[11],"with":[12,84],"social":[13,38,57,85,138],"norms":[14],"has":[15,23],"become":[16],"a":[17,32,50,103,121],"critical":[18],"concern.":[19],"While":[20],"prior":[21],"research":[22],"examined":[24],"bias":[25,111,158],"detection":[26],"in":[27,35,59,81,112,183],"various":[28],"languages,":[29],"there":[30],"remains":[31],"significant":[33,137],"gap":[34],"resources":[36],"addressing":[37],"biases":[39,58,139],"within":[40],"Persian":[41,60,113,141],"cultural":[42,67,168],"contexts.":[43],"In":[44],"this":[45],"work,":[46],"we":[47,151],"introduce":[48],"PBBQ,":[49],"comprehensive":[51],"benchmark":[52,117],"dataset":[53,95,176],"designed":[54],"to":[55,88,148],"evaluate":[56],"LLMs.":[61],"Our":[62,130],"benchmark,":[63],"which":[64],"encompasses":[65],"16":[66],"categories,":[68],"was":[69],"developed":[70],"through":[71],"questionnaires":[72],"completed":[73],"by":[74,144],"250":[75],"diverse":[76],"individuals":[77],"across":[78,140],"multiple":[79],"demographics,":[80],"close":[82],"collaboration":[83],"science":[86],"experts":[87],"ensure":[89],"its":[90],"validity.":[91],"The":[92],"resulting":[93],"PBBQ":[94,175],"contains":[96,190],"over":[97],"37,000":[98],"carefully":[99],"curated":[100],"questions,":[101],"providing":[102],"foundation":[104],"for":[105,181],"evaluation":[107],"and":[108,124,167],"mitigation":[109],"models.":[115],"We":[116],"several":[118],"open-source":[119],"LLMs,":[120],"closed-source":[122],"model,":[123],"Persian-specific":[125],"fine-tuned":[126],"on":[128],"PBBQ.":[129],"findings":[131],"reveal":[132],"that":[133,153],"current":[134],"LLMs":[135,154],"exhibit":[136],"culture.":[142],"Additionally,":[143],"comparing":[145],"model":[146],"outputs":[147],"human":[149,157],"responses,":[150],"observe":[152],"often":[155],"replicate":[156],"patterns,":[159],"highlighting":[160],"complex":[162],"interplay":[163],"between":[164],"learned":[165],"representations":[166],"stereotypes.Upon":[169],"acceptance":[170],"paper,":[173],"our":[174],"will":[177],"be":[178],"publicly":[179],"available":[180],"use":[182],"future":[184],"work.":[185],"Content":[186],"warning:":[187],"This":[188],"paper":[189],"unsafe":[191],"content.":[192]},"counts_by_year":[],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-24T00:00:00"}