{"id":"https://openalex.org/W7197036362","doi":"https://doi.org/10.48550/arxiv.2608.04186","title":"Large Language Models for Low-Resource Languages: A Conceptual Framework for an Electronic Explanatory Dictionary of the Tajik Language","display_name":"Large Language Models for Low-Resource Languages: A Conceptual Framework for an Electronic Explanatory Dictionary of the Tajik Language","publication_year":2026,"publication_date":"2026-08-04","ids":{"openalex":"https://openalex.org/W7197036362","doi":"https://doi.org/10.48550/arxiv.2608.04186"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.04186","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.04186","pdf_url":"https://arxiv.org/pdf/2608.04186","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.04186","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135642748","display_name":"Mullosharaf K. Arabov","orcid":"https://orcid.org/0000-0003-2525-1183","observed_orcids":["https://orcid.org/0000-0003-2525-1183"]},"institutions":[{"id":"https://openalex.org/I21203515","display_name":"Kazan Federal University","ror":"https://ror.org/05256ym39","country_code":"RU","type":"education","lineage":["https://openalex.org/I21203515"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Arabov, Mullosharaf K.","raw_affiliation_strings":["Kazan Federal University , Institute of Computational Mathematics and Information Technologies , Kazan , Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Kazan Federal University , Institute of Computational Mathematics and Information Technologies , Kazan , Russia","institution_ids":["https://openalex.org/I21203515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152466838","display_name":"Saidali M. Pirzoda","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pirzoda, Saidali M.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5006836798","display_name":"B. Sultonov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I172183325","display_name":"Tajik National University","ror":"https://ror.org/04bccg972","country_code":"TJ","type":"education","lineage":["https://openalex.org/I172183325"]}],"countries":["TJ"],"is_corresponding":false,"raw_author_name":"Sultonov, Behruz A.","raw_affiliation_strings":["Tajik National University , Department of Information and Communication Technologies , Faculty of Mechanics and Mathematics , Dushanbe , Tajikistan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tajik National University , Department of Information and Communication Technologies , Faculty of Mechanics and Mathematics , Dushanbe , Tajikistan","institution_ids":["https://openalex.org/I172183325"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.8310999870300293,"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":0.8310999870300293,"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/T12353","display_name":"Lexicography and Language Studies","score":0.16249999403953552,"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"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.00430000014603138,"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/tajik-language","display_name":"Tajik language","score":0.9919999837875366},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7480000257492065},{"id":"https://openalex.org/keywords/low-resource-languages","display_name":"low-resource languages","score":0.9879999756813049},{"id":"https://openalex.org/keywords/lexicography","display_name":"lexicography","score":0.8119999766349792},{"id":"https://openalex.org/keywords/morphological-analysis","display_name":"morphological analysis","score":0.9039999842643738},{"id":"https://openalex.org/keywords/lemmatization","display_name":"lemmatization","score":0.9850000143051147},{"id":"https://openalex.org/keywords/semantic-clustering","display_name":"semantic clustering","score":0.9890000224113464},{"id":"https://openalex.org/keywords/subword-tokenization","display_name":"subword tokenization","score":0.8849999904632568},{"id":"https://openalex.org/keywords/agglutinative-morphology","display_name":"agglutinative morphology","score":0.9290000200271606},{"id":"https://openalex.org/keywords/parameter-efficient-fine-tuning","display_name":"parameter-efficient fine-tuning","score":0.984000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8271999955177307},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6187999844551086},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5651999711990356},{"id":"https://openalex.org/C159254197","wikidata":"https://www.wikidata.org/wiki/Q1144915","display_name":"Lexicographical order","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.45089998841285706},{"id":"https://openalex.org/C83479923","wikidata":"https://www.wikidata.org/wiki/Q2063748","display_name":"Universal Networking Language","level":4,"score":0.43950000405311584},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.3837999999523163},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.3734999895095825},{"id":"https://openalex.org/C161831844","wikidata":"https://www.wikidata.org/wiki/Q2554325","display_name":"Lemmatisation","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C2779235283","wikidata":"https://www.wikidata.org/wiki/Q2640207","display_name":"Bilingual dictionary","level":2,"score":0.35850000381469727},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.3573000133037567},{"id":"https://openalex.org/C14224292","wikidata":"https://www.wikidata.org/wiki/Q13600188","display_name":"Conceptual framework","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C25810664","wikidata":"https://www.wikidata.org/wiki/Q44325","display_name":"Ontology","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.32739999890327454},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.3102000057697296},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.3089999854564667},{"id":"https://openalex.org/C2780403423","wikidata":"https://www.wikidata.org/wiki/Q6537700","display_name":"Lexical database","level":3,"score":0.305400013923645},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C129792486","wikidata":"https://www.wikidata.org/wiki/Q1050419","display_name":"Language identification","level":3,"score":0.30300000309944153},{"id":"https://openalex.org/C13606891","wikidata":"https://www.wikidata.org/wiki/Q2623243","display_name":"Conceptual model","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C80875076","wikidata":"https://www.wikidata.org/wiki/Q171263","display_name":"Agglutinative language","level":3,"score":0.2825999855995178},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.2799000144004822},{"id":"https://openalex.org/C522192633","wikidata":"https://www.wikidata.org/wiki/Q34228","display_name":"Sign language","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.27399998903274536},{"id":"https://openalex.org/C171686336","wikidata":"https://www.wikidata.org/wiki/Q3532085","display_name":"Topic model","level":2,"score":0.2678000032901764},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.04186","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.04186","pdf_url":"https://arxiv.org/pdf/2608.04186","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.04186","doi":"https://doi.org/10.48550/arxiv.2608.04186","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.04186","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.04186","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.04186","pdf_url":"https://arxiv.org/pdf/2608.04186","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7197036362.pdf","grobid_xml":"https://content.openalex.org/works/W7197036362.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W3181868922","https://openalex.org/W4376311954","https://openalex.org/W4402671031","https://openalex.org/W4407617384","https://openalex.org/W4411933307","https://openalex.org/W4412944503","https://openalex.org/W4412945622","https://openalex.org/W7155203046","https://openalex.org/W7160247692","https://openalex.org/W7160389600","https://openalex.org/W7160396613","https://openalex.org/W7160518378","https://openalex.org/W7160541324","https://openalex.org/W7162688387","https://openalex.org/W7166847697"],"related_works":["https://openalex.org/W4411933307","https://openalex.org/W7155203046","https://openalex.org/W7160541324","https://openalex.org/W7202078769","https://openalex.org/W4404780810","https://openalex.org/W4405633848","https://openalex.org/W4416236663","https://openalex.org/W7135226679","https://openalex.org/W7140130056","https://openalex.org/W7160396613"],"abstract_inverted_index":{"This":[0],"paper":[1,206],"presents":[2],"a":[3,31,65,77,116,158,171,176,185,190],"conceptual":[4,137],"framework":[5],"for":[6,36,45,83,122,143,174,193,209],"developing":[7,175],"an":[8,140],"electronic":[9,178],"explanatory":[10,141],"dictionary":[11,78,90,142,179],"of":[12,23,30,53,68,97,106,128,139,155,164,170,217],"the":[13,24,28,50,103,129,134,165,168],"Tajik":[14,37,107,144],"language":[15,18,56,61,150,219],"using":[16,93],"large":[17],"models":[19],"(LLMs).":[20],"The":[21,95,126,161,205],"relevance":[22],"work":[25,130],"stems":[26],"from":[27,49],"absence":[29],"comprehensive":[32],"digital":[33],"lexicographic":[34,148,186],"resource":[35,192],"that":[38,80,145,180],"is":[39,100,167,207],"comparable":[40],"in":[41,132,211],"functionality":[42],"to":[43,59],"dictionaries":[44],"high-resource":[46],"languages,":[47],"and":[48,72,89,109,152,188,200,215],"limited":[51,123],"adaptation":[52],"modern":[54],"natural":[55,218],"processing":[57,220],"technologies":[58],"low-resource":[60,224],"systems.":[62],"Based":[63],"on":[64],"systematic":[66],"survey":[67],"existing":[69],"linguistic,":[70],"statistical,":[71],"corpus":[73],"resources,":[74],"we":[75],"propose":[76],"architecture":[79,138],"integrates":[81],"modules":[82],"morphological":[84,112],"analysis,":[85,199],"lemmatization,":[86],"semantic":[87],"clustering,":[88],"entry":[91],"generation":[92],"LLMs.":[94],"choice":[96],"subword":[98],"tokenization":[99],"justified":[101],"by":[102],"agglutinative":[104],"nature":[105],"morphology":[108],"its":[110],"high":[111],"variability,":[113],"along":[114],"with":[115,223],"parameter-efficient":[117],"fine-tuning":[118],"(PEFT)":[119],"strategy":[120],"suitable":[121],"annotated":[124],"data.":[125],"novelty":[127],"lies":[131],"proposing":[133],"first":[135],"holistic":[136],"unifies":[146],"classical":[147],"methods,":[149],"statistics,":[151],"generative":[153],"capabilities":[154],"LLMs":[156],"into":[157],"single":[159],"system.":[160],"practical":[162],"significance":[163],"study":[166],"formation":[169],"methodological":[172],"foundation":[173],"full-featured":[177],"can":[181],"serve":[182],"both":[183],"as":[184,189],"tool":[187],"core":[191],"machine":[194],"translation,":[195],"automatic":[196],"summarization,":[197],"sentiment":[198],"other":[201],"applied":[202],"NLP":[203],"tasks.":[204],"intended":[208],"specialists":[210],"computational":[212],"linguistics,":[213],"lexicography,":[214],"developers":[216],"systems":[221],"working":[222],"languages.":[225]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-07T00:00:00"}
