{"id":"https://openalex.org/W4413178514","doi":"https://doi.org/10.3389/frai.2025.1538165","title":"Tokenization efficiency of current foundational large language models for the Ukrainian language","display_name":"Tokenization efficiency of current foundational large language models for the Ukrainian language","publication_year":2025,"publication_date":"2025-08-13","ids":{"openalex":"https://openalex.org/W4413178514","doi":"https://doi.org/10.3389/frai.2025.1538165","pmid":"https://pubmed.ncbi.nlm.nih.gov/40880881"},"language":"en","primary_location":{"id":"doi:10.3389/frai.2025.1538165","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1538165","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1538165/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1538165/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057157864","display_name":"Daniil Maksymenko","orcid":"https://orcid.org/0000-0003-3223-5130"},"institutions":[{"id":"https://openalex.org/I107158390","display_name":"Kharkiv National University of Radio Electronics","ror":"https://ror.org/01ctj1b90","country_code":"UA","type":"education","lineage":["https://openalex.org/I107158390"]},{"id":"https://openalex.org/I8765205","display_name":"V. N. Karazin Kharkiv National University","ror":"https://ror.org/03ftejk10","country_code":"UA","type":"education","lineage":["https://openalex.org/I8765205"]}],"countries":["UA"],"is_corresponding":false,"raw_author_name":"Daniil Maksymenko","raw_affiliation_strings":["Department of Artificial Intelligence, Kharkiv National University of Radio Electronics, Kharkiv, Ukraine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Kharkiv National University of Radio Electronics, Kharkiv, Ukraine","institution_ids":["https://openalex.org/I8765205","https://openalex.org/I107158390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085838790","display_name":"Oleksii Turuta","orcid":"https://orcid.org/0000-0002-0970-8617"},"institutions":[{"id":"https://openalex.org/I8765205","display_name":"V. N. Karazin Kharkiv National University","ror":"https://ror.org/03ftejk10","country_code":"UA","type":"education","lineage":["https://openalex.org/I8765205"]}],"countries":["UA"],"is_corresponding":true,"raw_author_name":"Oleksii Turuta","raw_affiliation_strings":["Computer Science and Artificial Intelligence Institution, V. N. Karazin Kharkiv National University, Kharkiv, Ukraine"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Artificial Intelligence Institution, V. N. Karazin Kharkiv National University, Kharkiv, Ukraine","institution_ids":["https://openalex.org/I8765205"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5085838790"],"corresponding_institution_ids":["https://openalex.org/I8765205"],"apc_list":{"value":1150,"currency":"USD","value_usd":1150},"apc_paid":{"value":1150,"currency":"USD","value_usd":1150},"fwci":1.7485,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87714425,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"8","issue":null,"first_page":"1538165","last_page":"1538165"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12734","display_name":"Information Systems and Technology Applications","score":0.8452000021934509,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12734","display_name":"Information Systems and Technology Applications","score":0.8452000021934509,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.7734000086784363,"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/lexical-analysis","display_name":"Lexical analysis","score":0.8388919234275818},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7810500860214233},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.6097038984298706},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5556650757789612},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5135486125946045},{"id":"https://openalex.org/keywords/transliteration","display_name":"Transliteration","score":0.5039510130882263},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49411872029304504},{"id":"https://openalex.org/keywords/ukrainian","display_name":"Ukrainian","score":0.42841649055480957},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.2889283001422882}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.8388919234275818},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7810500860214233},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.6097038984298706},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5556650757789612},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5135486125946045},{"id":"https://openalex.org/C520968082","wikidata":"https://www.wikidata.org/wiki/Q134550","display_name":"Transliteration","level":2,"score":0.5039510130882263},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49411872029304504},{"id":"https://openalex.org/C21931767","wikidata":"https://www.wikidata.org/wiki/Q8798","display_name":"Ukrainian","level":2,"score":0.42841649055480957},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.2889283001422882},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3389/frai.2025.1538165","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1538165","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1538165/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},{"id":"pmid:40880881","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40880881","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in artificial intelligence","raw_type":null},{"id":"pmh:oai:doaj.org/article:c56feee52a9e4d00b20c0767c7a3d48e","is_oa":true,"landing_page_url":"https://doaj.org/article/c56feee52a9e4d00b20c0767c7a3d48e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Frontiers in Artificial Intelligence, Vol 8 (2025)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:11189339","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12380774","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"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"}],"best_oa_location":{"id":"doi:10.3389/frai.2025.1538165","is_oa":true,"landing_page_url":"https://doi.org/10.3389/frai.2025.1538165","pdf_url":"https://public-pages-files-2025.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1538165/pdf","source":{"id":"https://openalex.org/S4210197006","display_name":"Frontiers in Artificial Intelligence","issn_l":"2624-8212","issn":["2624-8212"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320527","host_organization_name":"Frontiers Media","host_organization_lineage":["https://openalex.org/P4310320527"],"host_organization_lineage_names":["Frontiers Media"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4413178514.pdf","grobid_xml":"https://content.openalex.org/works/W4413178514.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W4225593490","https://openalex.org/W4327810158","https://openalex.org/W4378498597","https://openalex.org/W4381586770","https://openalex.org/W4384918448","https://openalex.org/W4386148021","https://openalex.org/W4387561528","https://openalex.org/W4388650715","https://openalex.org/W4389326242","https://openalex.org/W4390041933","https://openalex.org/W4390549066","https://openalex.org/W4390723197","https://openalex.org/W4392822465","https://openalex.org/W4394007799","https://openalex.org/W4395064864","https://openalex.org/W4395474395","https://openalex.org/W4401306886","https://openalex.org/W4401306979","https://openalex.org/W4401660192"],"related_works":["https://openalex.org/W3153459181","https://openalex.org/W2147866274","https://openalex.org/W2350015575","https://openalex.org/W4298195702","https://openalex.org/W2945402993","https://openalex.org/W4378498597","https://openalex.org/W3101140821","https://openalex.org/W4287816966","https://openalex.org/W3015650676","https://openalex.org/W4388347706"],"abstract_inverted_index":{"Foundational":[0],"large":[1],"language":[2,93,131],"models":[3,20],"(LLMs)":[4],"are":[5,37],"deployed":[6],"in":[7,39,50,89,127],"multilingual":[8],"environments":[9],"across":[10],"a":[11,104],"range":[12],"of":[13,60,70,91,101,129],"general":[14],"and":[15,29,62,94,124],"narrow":[16],"task":[17],"domains.":[18],"These":[19],"generate":[21],"text":[22],"token":[23],"by":[24],"token,":[25],"making":[26],"them":[27],"slower":[28],"more":[30,48,110],"computationally":[31],"expensive":[32],"for":[33,73,83],"low-resource":[34],"languages":[35],"that":[36],"underrepresented":[38],"the":[40,58,74,120],"tokenizer":[41],"vocabulary.":[42],"It":[43,77],"also":[44,78],"makes":[45],"their":[46],"usage":[47],"costly":[49],"such":[51],"cases,":[52],"as":[53,97,99],"pricing":[54],"usually":[55],"depends":[56],"on":[57],"number":[59],"input":[61],"output":[63],"tokens.":[64],"This":[65],"study":[66],"compares":[67],"multiple":[68],"tokenizers":[69],"pretrained":[71],"LLMs":[72],"Ukrainian":[75,130],"language.":[76],"provides":[79],"tokenization":[80,109],"fertility":[81],"measurements":[82],"current":[84,121],"state-of-the-art":[85],"(SOTA)":[86],"models,":[87],"both":[88],"terms":[90,128],"general-purpose":[92],"specific":[95],"domains,":[96],"well":[98],"results":[100,116],"experiments":[102],"with":[103],"transliteration":[105],"approach":[106],"to":[107],"make":[108],"efficient":[111],"without":[112],"information":[113],"loss.":[114],"The":[115],"provide":[117],"insights":[118],"into":[119],"models'":[122],"disadvantages":[123],"possible":[125],"problems":[126],"modeling.":[132]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-05-27T09:02:27.158192","created_date":"2025-10-10T00:00:00"}
