{"id":"https://openalex.org/W4414790523","doi":"https://doi.org/10.63317/3xhrjewfcyrm","title":"PerHalluEval: Persian Hallucination Evaluation Benchmark for Large Language Models","display_name":"PerHalluEval: Persian Hallucination Evaluation Benchmark for Large Language Models","publication_year":2026,"publication_date":"2026-04-30","ids":{"openalex":"https://openalex.org/W4414790523","doi":"https://doi.org/10.63317/3xhrjewfcyrm"},"language":"en","primary_location":{"id":"doi:10.63317/3xhrjewfcyrm","is_oa":false,"landing_page_url":"https://doi.org/10.63317/3xhrjewfcyrm","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/2509.21104","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004481021","display_name":"Mohammad Hosseini","orcid":"https://orcid.org/0000-0002-2385-985X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mohammad Hosseini","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Kimia Hosseini","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kimia Hosseini","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/A5084454717","display_name":"Zahra Zanjani","orcid":"https://orcid.org/0000-0003-4450-9397"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zahra Zanjani","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5015201403","display_name":"Saeedeh Momtazi","orcid":"https://orcid.org/0000-0002-8110-1342"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saeedeh Momtazi","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.00680272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3107","last_page":"3127"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13095","display_name":"Plant-based Medicinal Research","score":0.8482999801635742,"subfield":{"id":"https://openalex.org/subfields/3004","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T13095","display_name":"Plant-based Medicinal Research","score":0.8482999801635742,"subfield":{"id":"https://openalex.org/subfields/3004","display_name":"Pharmacology"},"field":{"id":"https://openalex.org/fields/30","display_name":"Pharmacology, Toxicology and Pharmaceutics"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12647","display_name":"Traditional Chinese Medicine Studies","score":0.8428000211715698,"subfield":{"id":"https://openalex.org/subfields/2707","display_name":"Complementary and alternative medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.7504000067710876,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/hallucinating","display_name":"Hallucinating","score":0.9031999707221985},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.807200014591217},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7197999954223633},{"id":"https://openalex.org/keywords/persian","display_name":"Persian","score":0.626800000667572},{"id":"https://openalex.org/keywords/grammaticality","display_name":"Grammaticality","score":0.4521999955177307},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.36320000886917114}],"concepts":[{"id":"https://openalex.org/C2911011789","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Hallucinating","level":2,"score":0.9031999707221985},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.807200014591217},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7197999954223633},{"id":"https://openalex.org/C2776527531","wikidata":"https://www.wikidata.org/wiki/Q9168","display_name":"Persian","level":2,"score":0.626800000667572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6044999957084656},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6015999913215637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5852000117301941},{"id":"https://openalex.org/C2779525943","wikidata":"https://www.wikidata.org/wiki/Q1187300","display_name":"Grammaticality","level":3,"score":0.4521999955177307},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C2780922921","wikidata":"https://www.wikidata.org/wiki/Q255189","display_name":"Paraphrase","level":2,"score":0.35339999198913574},{"id":"https://openalex.org/C2776224158","wikidata":"https://www.wikidata.org/wiki/Q187931","display_name":"Phrase","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3149000108242035},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31349998712539673},{"id":"https://openalex.org/C2908998935","wikidata":"https://www.wikidata.org/wiki/Q130741","display_name":"Visual Hallucination","level":2,"score":0.29600000381469727},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.289900004863739},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2727999985218048},{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.26969999074935913},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.2676999866962433}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.63317/3xhrjewfcyrm","is_oa":false,"landing_page_url":"https://doi.org/10.63317/3xhrjewfcyrm","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:2509.21104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.21104","pdf_url":"https://arxiv.org/pdf/2509.21104","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.2509.21104","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2509.21104","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:2509.21104","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2509.21104","pdf_url":"https://arxiv.org/pdf/2509.21104","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Hallucination":[0,20],"is":[1,22],"a":[2,37],"persistent":[3],"issue":[4],"affecting":[5],"all":[6],"large":[7],"language":[8],"Models":[9],"(LLMs),":[10],"particularly":[11],"within":[12],"low-resource":[13],"languages":[14],"such":[15],"as":[16],"Persian.":[17],"PerHalluEval":[18],"(Persian":[19],"Evaluation)":[21],"the":[23,31,66,74,90,120,136,140],"first":[24],"dynamic":[25],"hallucination":[26,145,156],"evaluation":[27,107],"benchmark":[28,35],"tailored":[29],"for":[30,139,162],"Persian":[32,104,127,163],"language.":[33],"Our":[34,106],"leverages":[36],"three-stage":[38],"LLM-driven":[39],"pipeline,":[40],"augmented":[41],"with":[42,164],"human":[43,83],"validation,":[44],"to":[45,72,85,95,103],"generate":[46],"plausible":[47],"answers":[48],"and":[49,53,60,113],"summaries":[50],"regarding":[51],"QA":[52,91],"summarization":[54,141],"tasks,":[55],"focusing":[56],"on":[57,99],"detecting":[58,125],"extrinsic":[59],"intrinsic":[61],"hallucinations.":[62],"Moreover,":[63],"we":[64,81],"used":[65],"log":[67],"probabilities":[68],"of":[69,108,155],"generated":[70],"tokens":[71],"select":[73],"most":[75],"believable":[76],"hallucinated":[77,126],"instances.":[78],"In":[79],"addition,":[80],"engaged":[82],"annotators":[84],"highlight":[86],"Persian-specific":[87],"contexts":[88],"in":[89,93,124,153],"dataset":[92],"order":[94],"evaluate":[96],"LLMs'":[97],"performance":[98],"content":[100],"specifically":[101,160],"related":[102],"culture.":[105],"12":[109],"LLMs,":[110],"including":[111],"open-":[112],"closed-source":[114],"models":[115,121],"using":[116],"PerHalluEval,":[117],"revealed":[118],"that":[119,131],"generally":[122],"struggle":[123],"text.":[128],"We":[129],"showed":[130],"providing":[132],"external":[133],"knowledge,":[134],"i.e.,":[135],"original":[137],"document":[138],"task,":[142],"could":[143],"mitigate":[144],"partially.":[146],"Furthermore,":[147],"there":[148],"was":[149],"no":[150],"significant":[151],"difference":[152],"terms":[154],"when":[157],"comparing":[158],"LLMs":[159],"trained":[161],"others.":[165]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}