{"id":"https://openalex.org/W7140100428","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.291","title":"Do LLMs model human linguistic variation? A case study in Hindi-English Verb code-mixing","display_name":"Do LLMs model human linguistic variation? A case study in Hindi-English Verb code-mixing","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140100428","doi":"https://doi.org/10.18653/v1/2026.findings-eacl.291"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.findings-eacl.291","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.291","pdf_url":"https://aclanthology.org/2026.findings-eacl.291.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: EACL 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.findings-eacl.291.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069473673","display_name":"Mukund Choudhary","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mukund Choudhary","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102784129","display_name":"M. K. Jindal","orcid":"https://orcid.org/0000-0002-4429-5424"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Madhur Jindal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130324818","display_name":"Gaurja Aeron","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gaurja Aeron","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130350520","display_name":"Monojit Choudhury","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Monojit Choudhury","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":0.24736674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5491","last_page":"5509"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.5235000252723694,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.5235000252723694,"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":0.08510000258684158,"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"}},{"id":"https://openalex.org/T10034","display_name":"Syntax, Semantics, Linguistic Variation","score":0.05829999968409538,"subfield":{"id":"https://openalex.org/subfields/1203","display_name":"Language and Linguistics"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/verb","display_name":"Verb","score":0.5163000226020813},{"id":"https://openalex.org/keywords/argument","display_name":"Argument (complex analysis)","score":0.2614000141620636},{"id":"https://openalex.org/keywords/style","display_name":"Style (visual arts)","score":0.2533999979496002},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.24539999663829803}],"concepts":[{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.708899974822998},{"id":"https://openalex.org/C2776397901","wikidata":"https://www.wikidata.org/wiki/Q24905","display_name":"Verb","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.36559998989105225},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.2759999930858612},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.2694000005722046},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.2614000141620636},{"id":"https://openalex.org/C2776445246","wikidata":"https://www.wikidata.org/wiki/Q1792644","display_name":"Style (visual arts)","level":2,"score":0.2533999979496002},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.2513999938964844},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.24539999663829803},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2443999946117401}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.findings-eacl.291","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.291","pdf_url":"https://aclanthology.org/2026.findings-eacl.291.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: EACL 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.findings-eacl.291","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-eacl.291","pdf_url":"https://aclanthology.org/2026.findings-eacl.291.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: EACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.6562837362289429,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7140100428.pdf","grobid_xml":"https://content.openalex.org/works/W7140100428.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Do":[0],"large":[1],"language":[2,43,64,75],"models":[3,89],"(LLMs)":[4],"model":[5],"linguistic":[6],"variation?We":[7],"investigate":[8],"this":[9],"question":[10],"through":[11],"Hindi-English":[12],"(Hinglish)":[13],"verb":[14,23,27,31,74,105,111],"codemixing,":[15],"where":[16],"speakers":[17,38],"can":[18],"use":[19],"either":[20],"a":[21],"Hindi":[22],"or":[24],"an":[25,95],"English":[26],"with":[28,85],"the":[29,46],"light":[30],"karna":[32],"('do').Both":[33],"forms":[34],"are":[35],"grammatical,":[36],"but":[37],"show":[39],"unexplained":[40],"variation":[41],"in":[42],"choice":[44],"for":[45,109],"verb.We":[47],"compare":[48],"human":[49,92],"preferences":[50,76],"on":[51,103],"controlled":[52],"code-mixed":[53],"minimal":[54],"pairs":[55,112],"to":[56,77,94],"LLM":[57],"perplexities":[58],"spanning":[59],"families,":[60],"sizes,":[61],"and":[62,116],"training":[63],"compositions.We":[65],"find":[66],"that":[67,84],"current":[68],"LLMs":[69],"do":[70,90],"not":[71],"reliably":[72],"classify":[73],"match":[78],"native":[79,99],"speaker":[80,100],"judgments.We":[81],"also":[82],"see":[83],"specific":[86],"supervision,":[87],"some":[88],"predict":[91],"preference":[93],"extent.We":[96],"release":[97],"(here)":[98],"acceptability":[101],"judgments":[102],"30":[104],"pairs,":[106],"perplexity":[107],"ratios":[108],"4,279":[110],"across":[113],"7":[114],"models,":[115],"experimental":[117],"materials.":[118]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-03-24T00:00:00"}