{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T06:40:25Z","timestamp":1776235225145,"version":"3.50.1"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100002635","name":"Inha University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002635","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3679427","type":"journal-article","created":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T19:53:21Z","timestamp":1774986801000},"page":"1-1","source":"Crossref","is-referenced-by-count":0,"title":["Efficient LLM Adaptation to Low-Resource Languages via Cross-Lingual Semantic Anchoring"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3061-3368","authenticated-orcid":false,"given":"Bekhzod","family":"Shukhratov","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Inha University, Incheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9255-8068","authenticated-orcid":false,"given":"Shokhrukh","family":"Baydadaev","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Inha University, Incheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2097-557X","authenticated-orcid":false,"given":"Jang Woo","family":"Kwon","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Inha University, Incheon, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"3823","article-title":"Do large language models have an English accent? Evaluating and improving the naturalness of multilingual LLMs","volume-title":"Proc. 63rd Annu. Meeting Assoc. Comput. Linguistics","author":"Guo"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/access.2025.3570699"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.243"},{"key":"ref4","first-page":"36963","article-title":"Language model tokenizers introduce unfairness between languages","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Petrov"},{"key":"ref5","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref6","article-title":"How does a language-specific tokenizer affect LLMs?","author":"Seo","year":"2025","journal-title":"arXiv:2502.12560"},{"key":"ref7","first-page":"7059","article-title":"Cross-lingual language model pretraining","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Conneau"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.62"},{"key":"ref9","article-title":"From English-centric to effective bilingual: LLMs with custom tokenizers for underrepresented languages","author":"Kiulian","year":"2024","journal-title":"arXiv:2410.18836"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.139"},{"key":"ref11","article-title":"Trans-tokenization and cross-lingual vocabulary transfers: Language adaptation of LLMs for low-resource NLP","volume-title":"Proc. 1st Conf. Lang. Model. (COLM)","author":"Remy"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref13","volume-title":"BERT: BertConfig Documentation","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5916\/jkosme.2014.38.5.557"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/access.2023.3281680"},{"key":"ref17","article-title":"Aya expanse: Combining research breakthroughs for a new multilingual frontier","author":"Dang","year":"2024","journal-title":"arXiv:2412.04261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.61"},{"key":"ref19","article-title":"Efficient estimation of word representations in vector space","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mikolov"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1162"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-76153-9_28"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref23","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00474"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w18-6319"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.213"},{"key":"ref27","volume-title":"Behbudiy\/Uzbek-Sentiment-Analysis","author":"Mansurov","year":"2022"},{"key":"ref28","volume-title":"Risqaliyevds\/Uzbek-Zero-Shot-Classification","author":"Risqaliyev","year":"2023"},{"key":"ref29","article-title":"Measuring massive multitask language understanding","volume-title":"Proc. 9th Int. Conf. Learning Represent.","author":"Hendrycks"},{"key":"ref30","article-title":"Gemma: Open models based on Gemini research and technology","author":"Mesnard","year":"2024","journal-title":"arXiv:2403.08295"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-2012"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref33","volume-title":"Korean_sentiment","year":"2023"},{"key":"ref34","volume-title":"Korean-FineTome-100k-Classification-Korean","year":"2024"},{"key":"ref35","first-page":"258","article-title":"XLM-T: Multilingual language models in Twitter for sentiment analysis and beyond","volume-title":"Proc. 13th Lang. Resour. Eval. Conf. (LREC)","author":"Barbieri"},{"key":"ref36","article-title":"MTEB: Massive text embedding benchmark","author":"Muennighoff","year":"2022","journal-title":"arXiv:2210.07316"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.441"},{"key":"ref38","volume-title":"Wikipedia","year":"2022"},{"key":"ref39","volume-title":"Uz-crawl","year":"2023"},{"key":"ref40","volume-title":"Uz-Wiki","author":"Mansurov","year":"2023"},{"key":"ref41","first-page":"30811","article-title":"The FineWeb datasets: Decanting the web for the finest text data at scale","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Allal"},{"key":"ref42","volume-title":"Alpaca","year":"2023"},{"key":"ref43","volume-title":"Uzbek-Instruct-Llm","author":"Azimov","year":"2024"},{"key":"ref44","volume-title":"Alpaca-Cleaned-uz","year":"2023"},{"key":"ref45","volume-title":"Translation-Instruction","year":"2024"},{"key":"ref46","volume-title":"KOREAN-WEBTEXT: A High-Quality Korean Language Corpus","year":"2024"},{"key":"ref47","volume-title":"Wikipedia","year":"2023"},{"key":"ref48","volume-title":"Kullm-v2","year":"2023"},{"key":"ref49","volume-title":"Alpaca-Spanish","year":"2023"},{"key":"ref50","volume-title":"Alpaca-Malay-Cleaned","year":"2024"},{"key":"ref51","volume-title":"Combined-Malay-Sentiment","author":"Razak","year":"2024"},{"key":"ref52","volume-title":"Newsdataset-Ind-Classification","year":"2023"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/6514899\/11458819.pdf?arnumber=11458819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T05:40:25Z","timestamp":1776231625000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11458819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":52,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3679427","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}