{"id":"https://openalex.org/W4391463129","doi":"https://doi.org/10.18653/v1/2026.acl-long.1922","title":"Paramanu: Compact and Competitive Monolingual Language Models for Low-Resource Morphologically Rich Indian Languages","display_name":"Paramanu: Compact and Competitive Monolingual Language Models for Low-Resource Morphologically Rich Indian Languages","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4391463129","doi":"https://doi.org/10.18653/v1/2026.acl-long.1922"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.acl-long.1922","doi":"https://doi.org/10.18653/v1/2026.acl-long.1922","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1922","pdf_url":"https://aclanthology.org/2026.acl-long.1922.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://aclanthology.org/2026.acl-long.1922.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040409857","display_name":"Mitodru Niyogi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Mitodru Niyogi","raw_affiliation_strings":["Universit\u00e9 Grenoble Alpes , CNRS , Grenoble INP , LIG , 38000 Grenoble , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Grenoble Alpes , CNRS , Grenoble INP , LIG , 38000 Grenoble , France","institution_ids":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210104430","https://openalex.org/I899635006"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014352159","display_name":"\u00c9ric Gaussier","orcid":"https://orcid.org/0000-0002-8858-3233","observed_orcids":["https://orcid.org/0000-0002-8858-3233"]},"institutions":[{"id":"https://openalex.org/I106785703","display_name":"Institut polytechnique de Grenoble","ror":"https://ror.org/05sbt2524","country_code":"FR","type":"education","lineage":["https://openalex.org/I106785703","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I4210104430","display_name":"Laboratoire d'Informatique de Grenoble","ror":"https://ror.org/01c8rcg82","country_code":"FR","type":"facility","lineage":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I1326498283","https://openalex.org/I4210104430","https://openalex.org/I4210159245","https://openalex.org/I899635006"]},{"id":"https://openalex.org/I899635006","display_name":"Universit\u00e9 Grenoble Alpes","ror":"https://ror.org/02rx3b187","country_code":"FR","type":"education","lineage":["https://openalex.org/I899635006"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Eric Gaussier","raw_affiliation_strings":["Universit\u00e9 Grenoble Alpes , CNRS , Grenoble INP , LIG , 38000 Grenoble , France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Grenoble Alpes , CNRS , Grenoble INP , LIG , 38000 Grenoble , France","institution_ids":["https://openalex.org/I106785703","https://openalex.org/I1294671590","https://openalex.org/I4210104430","https://openalex.org/I899635006"]}]},{"author_position":"last","author":{"id":null,"display_name":"Arnab Bhattacharya","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I94234084","display_name":"Indian Institute of Technology Kanpur","ror":"https://ror.org/05pjsgx75","country_code":"IN","type":"education","lineage":["https://openalex.org/I94234084"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Arnab Bhattacharya","raw_affiliation_strings":["Dept. of Computer Science and Engineering , Indian Institute of Technology Kanpur , India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science and Engineering , Indian Institute of Technology Kanpur , India","institution_ids":["https://openalex.org/I94234084"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.00086382,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"41431","last_page":"41458"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.6977999806404114,"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":0.6977999806404114,"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":0.29319998621940613,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.0020000000949949026,"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/monolingual-language-models","display_name":"monolingual language models","score":0.9279999732971191},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.8970000147819519},{"id":"https://openalex.org/keywords/morphologically-rich-languages","display_name":"morphologically rich languages","score":0.9470000267028809},{"id":"https://openalex.org/keywords/indian-languages","display_name":"Indian languages","score":0.9769999980926514},{"id":"https://openalex.org/keywords/bengali-language","display_name":"Bengali language","score":0.7839999794960022},{"id":"https://openalex.org/keywords/hindi","display_name":"Hindi","score":0.9990000128746033},{"id":"https://openalex.org/keywords/marathi","display_name":"Marathi language","score":0.9940000176429749},{"id":"https://openalex.org/keywords/tamil","display_name":"Tamil language","score":1.0},{"id":"https://openalex.org/keywords/telugu","display_name":"Telugu","score":1.0},{"id":"https://openalex.org/keywords/instruction-tuning-dataset","display_name":"instruction-tuning dataset","score":0.7710000276565552}],"concepts":[{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.8030440807342529},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.7778458595275879},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.5146730542182922},{"id":"https://openalex.org/C2780566098","wikidata":"https://www.wikidata.org/wiki/Q25295","display_name":"Language family","level":2,"score":0.41399484872817993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3787882626056671},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.36059677600860596},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35947132110595703},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.3271132707595825},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.278433233499527},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.1801573634147644},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.08307138085365295}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.1922","doi":"https://doi.org/10.18653/v1/2026.acl-long.1922","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1922","pdf_url":"https://aclanthology.org/2026.acl-long.1922.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2401.18034","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.18034","pdf_url":"https://arxiv.org/pdf/2401.18034","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2401.18034","doi":"https://doi.org/10.48550/arxiv.2401.18034","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.18034","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.1922","doi":"https://doi.org/10.18653/v1/2026.acl-long.1922","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.1922","pdf_url":"https://aclanthology.org/2026.acl-long.1922.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G4306980366","display_name":"General pUrpose dIalogue-based DigitAl iNformation acCEss","funder_award_id":"ANR-23-IAS1-0003","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G7080048889","display_name":null,"funder_award_id":"ANR-23","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"}],"funders":[{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320322893","display_name":"Institut Universitaire de France","ror":"https://ror.org/055khg266"},{"id":"https://openalex.org/F4320326256","display_name":"Grand \u00c9quipement National De Calcul Intensif","ror":"https://ror.org/0010d1q40"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391463129.pdf","grobid_xml":"https://content.openalex.org/works/W4391463129.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7164013048","https://openalex.org/W7133903448","https://openalex.org/W4416453712","https://openalex.org/W3118580427","https://openalex.org/W7140141361","https://openalex.org/W4416280587","https://openalex.org/W7163905643","https://openalex.org/W4416933449","https://openalex.org/W4402426770","https://openalex.org/W4412889440"],"abstract_inverted_index":{"Multilingual":[0],"large":[1],"language":[2,40,86],"models":[3,41,63,145,153],"(LLMs)":[4],"are":[5,64,69,121,156],"expensive":[6],"to":[7,83,109,124,147],"pretrain":[8],"and":[9,16,27,61,68,96,140,154],"often":[10],"suffer":[11],"from":[12,43],"imbalances":[13],"across":[14,149],"languages":[15],"datasets,":[17],"English-centric":[18],"bias,":[19],"tokenizer":[20],"oversegmentation":[21],"for":[22,49,66,101],"morphologically":[23],"rich":[24],"low-resource":[25],"languages,":[26],"the":[28,50,125],"curse":[29],"of":[30,36],"multilinguality.We":[31],"introduce":[32],"PARAMANU,":[33],"a":[34,72,76,136],"family":[35],"Indian":[37,54],"language-only":[38],"autoregressive":[39],"trained":[42,70],"scratch":[44],"on":[45,71],"open-source":[46],"language-specific":[47],"data":[48],"five":[51,151],"most":[52,142],"spoken":[53],"languages:":[55],"Bangla":[56,119],"(Bengali),":[57],"Hindi,":[58],"Marathi,":[59],"Tamil,":[60],"Telugu.All":[62],"designed":[65],"affordability":[67],"single":[73],"GPU":[74],"with":[75],"budget":[77],"under":[78],"$1,000,":[79],"allowing":[80],"under-resourced":[81],"researchers":[82],"build":[84],"competitive":[85],"models.To":[87],"address":[88],"lowresource":[89],"challenges,":[90],"we":[91],"develop":[92],"morphologyaligned,":[93],"low-fertility":[94],"tokenizers,":[95],"propose":[97],"an":[98],"interpolation-based":[99],"method":[100],"token":[102],"position":[103],"indices":[104],"in":[105,118],"RoPE":[106],"based":[107],"scaling":[108],"train":[110],"longer":[111],"sequences":[112],"efficiently.We":[113],"also":[114],"create":[115],"instruction-tuning":[116],"datasets":[117,155],"that":[120],"then":[122],"translated":[123],"other":[126],"four":[127],"languages.Despite":[128],"their":[129],"small":[130],"size":[131],"(108M-367M":[132],"parameters),":[133],"Paramanu":[134],"achieves":[135],"strong":[137],"performance-efficiency":[138],"tradeoff":[139],"outperforms":[141],"larger":[143],"multilingual":[144],"up":[146],"8B":[148],"all":[150],"languages.The":[152],"available":[157],"at:":[158],"https://huggingface.":[159],"co/collections/mitodru/paramanu.":[160]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2024-02-02T00:00:00"}