MIGRATE: Cross-Lingual Adaptation of Domain-Specific LLMs through Code-Switching and Embedding Transfer. Hong, S., Lee, S., Moon, H., & Lim, H. In Rambow, O., Wanner, L., Apidianaki, M., Al-Khalifa, H., Eugenio, B. D., & Schockaert, S., editors, Proceedings of the 31st International Conference on Computational Linguistics, pages 9184–9193, Abu Dhabi, UAE, January, 2025. Association for Computational Linguistics. ![MIGRATE: Cross-Lingual Adaptation of Domain-Specific LLMs through Code-Switching and Embedding Transfer [link]](https://bibbase.org/img/filetypes/link.svg "link")
Paper abstract bibtex Large Language Models (LLMs) have rapidly advanced, with domain-specific expert models emerging to handle specialized tasks across various fields. However, the predominant focus on English-centric models demands extensive data, making it challenging to develop comparable models for middle and low-resource languages. To address this limitation, we introduce Migrate, a novel method that leverages open-source static embedding models and up to 3 million tokens of code-switching data to facilitate the seamless transfer of embeddings to target languages. Migrate enables effective cross-lingual adaptation without requiring large-scale domain-specific corpora in the target language, promoting the accessibility of expert LLMs to a diverse range of linguistic communities. Our experimental results demonstrate that Migrate significantly enhances model performance in target languages, outperforming baseline and existing cross-lingual transfer methods. This approach provides a practical and efficient solution for extending the capabilities of domain-specific expert models.
@inproceedings{hong_migrate_2025,
address = {Abu Dhabi, UAE},
title = {{MIGRATE}: {Cross}-{Lingual} {Adaptation} of {Domain}-{Specific} {LLMs} through {Code}-{Switching} and {Embedding} {Transfer}},
shorttitle = {{MIGRATE}},
url = {https://aclanthology.org/2025.coling-main.617/},
abstract = {Large Language Models (LLMs) have rapidly advanced, with domain-specific expert models emerging to handle specialized tasks across various fields. However, the predominant focus on English-centric models demands extensive data, making it challenging to develop comparable models for middle and low-resource languages. To address this limitation, we introduce Migrate, a novel method that leverages open-source static embedding models and up to 3 million tokens of code-switching data to facilitate the seamless transfer of embeddings to target languages. Migrate enables effective cross-lingual adaptation without requiring large-scale domain-specific corpora in the target language, promoting the accessibility of expert LLMs to a diverse range of linguistic communities. Our experimental results demonstrate that Migrate significantly enhances model performance in target languages, outperforming baseline and existing cross-lingual transfer methods. This approach provides a practical and efficient solution for extending the capabilities of domain-specific expert models.},
urldate = {2025-01-28},
booktitle = {Proceedings of the 31st {International} {Conference} on {Computational} {Linguistics}},
publisher = {Association for Computational Linguistics},
author = {Hong, Seongtae and Lee, Seungyoon and Moon, Hyeonseok and Lim, Heuiseok},
editor = {Rambow, Owen and Wanner, Leo and Apidianaki, Marianna and Al-Khalifa, Hend and Eugenio, Barbara Di and Schockaert, Steven},
month = jan,
year = {2025},
keywords = {coling-25},
pages = {9184--9193},
}
Downloads: 0
{"_id":"4z9NSqsGcZfrEigoy","bibbaseid":"hong-lee-moon-lim-migratecrosslingualadaptationofdomainspecificllmsthroughcodeswitchingandembeddingtransfer-2025","author_short":["Hong, S.","Lee, S.","Moon, H.","Lim, H."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","address":"Abu Dhabi, UAE","title":"MIGRATE: Cross-Lingual Adaptation of Domain-Specific LLMs through Code-Switching and Embedding Transfer","shorttitle":"MIGRATE","url":"https://aclanthology.org/2025.coling-main.617/","abstract":"Large Language Models (LLMs) have rapidly advanced, with domain-specific expert models emerging to handle specialized tasks across various fields. However, the predominant focus on English-centric models demands extensive data, making it challenging to develop comparable models for middle and low-resource languages. To address this limitation, we introduce Migrate, a novel method that leverages open-source static embedding models and up to 3 million tokens of code-switching data to facilitate the seamless transfer of embeddings to target languages. Migrate enables effective cross-lingual adaptation without requiring large-scale domain-specific corpora in the target language, promoting the accessibility of expert LLMs to a diverse range of linguistic communities. Our experimental results demonstrate that Migrate significantly enhances model performance in target languages, outperforming baseline and existing cross-lingual transfer methods. This approach provides a practical and efficient solution for extending the capabilities of domain-specific expert models.","urldate":"2025-01-28","booktitle":"Proceedings of the 31st International Conference on Computational Linguistics","publisher":"Association for Computational Linguistics","author":[{"propositions":[],"lastnames":["Hong"],"firstnames":["Seongtae"],"suffixes":[]},{"propositions":[],"lastnames":["Lee"],"firstnames":["Seungyoon"],"suffixes":[]},{"propositions":[],"lastnames":["Moon"],"firstnames":["Hyeonseok"],"suffixes":[]},{"propositions":[],"lastnames":["Lim"],"firstnames":["Heuiseok"],"suffixes":[]}],"editor":[{"propositions":[],"lastnames":["Rambow"],"firstnames":["Owen"],"suffixes":[]},{"propositions":[],"lastnames":["Wanner"],"firstnames":["Leo"],"suffixes":[]},{"propositions":[],"lastnames":["Apidianaki"],"firstnames":["Marianna"],"suffixes":[]},{"propositions":[],"lastnames":["Al-Khalifa"],"firstnames":["Hend"],"suffixes":[]},{"propositions":[],"lastnames":["Eugenio"],"firstnames":["Barbara","Di"],"suffixes":[]},{"propositions":[],"lastnames":["Schockaert"],"firstnames":["Steven"],"suffixes":[]}],"month":"January","year":"2025","keywords":"coling-25","pages":"9184–9193","bibtex":"@inproceedings{hong_migrate_2025,\n\taddress = {Abu Dhabi, UAE},\n\ttitle = {{MIGRATE}: {Cross}-{Lingual} {Adaptation} of {Domain}-{Specific} {LLMs} through {Code}-{Switching} and {Embedding} {Transfer}},\n\tshorttitle = {{MIGRATE}},\n\turl = {https://aclanthology.org/2025.coling-main.617/},\n\tabstract = {Large Language Models (LLMs) have rapidly advanced, with domain-specific expert models emerging to handle specialized tasks across various fields. However, the predominant focus on English-centric models demands extensive data, making it challenging to develop comparable models for middle and low-resource languages. To address this limitation, we introduce Migrate, a novel method that leverages open-source static embedding models and up to 3 million tokens of code-switching data to facilitate the seamless transfer of embeddings to target languages. Migrate enables effective cross-lingual adaptation without requiring large-scale domain-specific corpora in the target language, promoting the accessibility of expert LLMs to a diverse range of linguistic communities. Our experimental results demonstrate that Migrate significantly enhances model performance in target languages, outperforming baseline and existing cross-lingual transfer methods. This approach provides a practical and efficient solution for extending the capabilities of domain-specific expert models.},\n\turldate = {2025-01-28},\n\tbooktitle = {Proceedings of the 31st {International} {Conference} on {Computational} {Linguistics}},\n\tpublisher = {Association for Computational Linguistics},\n\tauthor = {Hong, Seongtae and Lee, Seungyoon and Moon, Hyeonseok and Lim, Heuiseok},\n\teditor = {Rambow, Owen and Wanner, Leo and Apidianaki, Marianna and Al-Khalifa, Hend and Eugenio, Barbara Di and Schockaert, Steven},\n\tmonth = jan,\n\tyear = {2025},\n\tkeywords = {coling-25},\n\tpages = {9184--9193},\n}\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n\n","author_short":["Hong, S.","Lee, S.","Moon, H.","Lim, H."],"editor_short":["Rambow, O.","Wanner, L.","Apidianaki, M.","Al-Khalifa, H.","Eugenio, B. D.","Schockaert, S."],"key":"hong_migrate_2025","id":"hong_migrate_2025","bibbaseid":"hong-lee-moon-lim-migratecrosslingualadaptationofdomainspecificllmsthroughcodeswitchingandembeddingtransfer-2025","role":"author","urls":{"Paper":"https://aclanthology.org/2025.coling-main.617/"},"keyword":["coling-25"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/zotero/abhishek-p","dataSources":["h7kKWXpJh2iaX92T5"],"keywords":["coling-25"],"search_terms":["migrate","cross","lingual","adaptation","domain","specific","llms","through","code","switching","embedding","transfer","hong","lee","moon","lim"],"title":"MIGRATE: Cross-Lingual Adaptation of Domain-Specific LLMs through Code-Switching and Embedding Transfer","year":2025}