{"id":"https://openalex.org/W4417163107","doi":"https://doi.org/10.18653/v1/2026.findings-acl.29","title":"UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu","display_name":"UrBLiMP: A Benchmark for Evaluating the Linguistic Competence of Large Language Models in Urdu","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417163107","doi":"https://doi.org/10.18653/v1/2026.findings-acl.29"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.29","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.29","pdf_url":"https://aclanthology.org/2026.findings-acl.29.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.29.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034131804","display_name":"Farah Adeeba","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Farah Adeeba","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036963045","display_name":"Brian Dillon","orcid":"https://orcid.org/0009-0001-3574-3889"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Brian Dillon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042954793","display_name":"Hassan Sajjad","orcid":"https://orcid.org/0000-0002-8584-6595"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hassan Sajjad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5102986621","display_name":"Rajesh Bhatt","orcid":"https://orcid.org/0000-0003-3059-2249"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajesh Bhatt","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":0.03459568,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"602","last_page":"617"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3118000030517578,"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":0.3118000030517578,"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":0.2240999937057495,"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/T13629","display_name":"Text Readability and Simplification","score":0.07769999653100967,"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/urdu","display_name":"Urdu","score":0.7994999885559082},{"id":"https://openalex.org/keywords/linguistic-competence","display_name":"Linguistic competence","score":0.5239999890327454},{"id":"https://openalex.org/keywords/competence","display_name":"Competence (human resources)","score":0.4758000075817108},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4650999903678894},{"id":"https://openalex.org/keywords/treebank","display_name":"Treebank","score":0.4185999929904938},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.40619999170303345}],"concepts":[{"id":"https://openalex.org/C2777350258","wikidata":"https://www.wikidata.org/wiki/Q1617","display_name":"Urdu","level":2,"score":0.7994999885559082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6442000269889832},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.616100013256073},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.6157000064849854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6078000068664551},{"id":"https://openalex.org/C17601614","wikidata":"https://www.wikidata.org/wiki/Q1346205","display_name":"Linguistic competence","level":2,"score":0.5239999890327454},{"id":"https://openalex.org/C100521375","wikidata":"https://www.wikidata.org/wiki/Q2015382","display_name":"Competence (human resources)","level":2,"score":0.4758000075817108},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4650999903678894},{"id":"https://openalex.org/C206134035","wikidata":"https://www.wikidata.org/wiki/Q811525","display_name":"Treebank","level":3,"score":0.4185999929904938},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.40619999170303345},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2904999852180481},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.27630001306533813},{"id":"https://openalex.org/C1701360","wikidata":"https://www.wikidata.org/wiki/Q192625","display_name":"Linguistic typology","level":3,"score":0.2615000009536743},{"id":"https://openalex.org/C2776230583","wikidata":"https://www.wikidata.org/wiki/Q1322198","display_name":"Spoken language","level":2,"score":0.2614000141620636}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.29","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.29","pdf_url":"https://aclanthology.org/2026.findings-acl.29.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2508.01006","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.01006","pdf_url":"https://arxiv.org/pdf/2508.01006","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.2508.01006","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.01006","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-acl.29","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.29","pdf_url":"https://aclanthology.org/2026.findings-acl.29.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":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417163107.pdf","grobid_xml":"https://content.openalex.org/works/W4417163107.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Evaluating":[0],"how":[1],"large":[2],"language":[3],"models":[4,105],"(LLMs)":[5],"capture":[6],"the":[7,17,48,78,87,121,135],"grammatical":[8,33],"structure":[9],"of":[10,20,27,140],"low-resource":[11,146],"languages":[12],"remains":[13],"underexplored.This":[14],"paper":[15],"presents":[16],"Urdu":[18,49,131],"Benchmark":[19],"Linguistic":[21],"Minimal":[22],"Pairs":[23],"(UrBLiMP)-a":[24],"diagnostic":[25],"suite":[26],"5,696":[28],"minimal":[29],"pairs":[30],"that":[31],"contrast":[32],"acceptability":[34],"across":[35],"ten":[36],"core":[37],"syntactic":[38,111],"and":[39,51,55,73,75,102,116,132,137,142],"morpho-syntactic":[40,128],"phenomena":[41,97],"in":[42,130,145],"Urdu.The":[43],"dataset":[44],"is":[45],"constructed":[46],"from":[47],"Treebank":[50],"diverse":[52],"text":[53],"corpora,":[54],"human":[56],"validation":[57],"achieves":[58],"a":[59],"96.1%":[60],"inter-annotator":[61],"agreement,":[62],"confirming":[63],"its":[64],"reliability.We":[65],"evaluate":[66],"twenty":[67],"one":[68],"multilingual":[69,141],"LLMs,":[70],"including":[71],"LLaMA-3-70B":[72],"Gemma-3-27B-PT,":[74],"additionally":[76],"assess":[77],"proprietary":[79,143],"GPT-4o":[80],"model":[81],"using":[82],"grammar-prompting":[83],"techniques.GPT-4o":[84],"(grammar-prompted)":[85],"attains":[86],"highest":[88],"average":[89],"accuracy":[90],"(97.4%),":[91],"reaching":[92],"nearhuman":[93],"performance":[94],"on":[95],"regular":[96],"such":[98],"as":[99],"aspect":[100],"agreement":[101],"ergativity.However,":[103],"all":[104],"continue":[106],"to":[107],"struggle":[108],"with":[109],"flexible":[110],"patterns":[112],"like":[113],"word-order":[114],"variation":[115],"long-distance":[117],"subject-verb":[118],"agreement.UrBLiMP":[119],"provides":[120],"first":[122],"controlled":[123],"evaluation":[124],"framework":[125],"for":[126],"probing":[127],"competence":[129],"highlights":[133],"both":[134],"progress":[136],"remaining":[138],"challenges":[139],"LLMs":[144],"settings.":[147]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}