Soft Language Prompts for Language Transfer. Vykopal, I., Ostermann, S., & Simko, M. In Chiruzzo, L., Ritter, A., & Wang, L., editors, Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 10294–10313, Albuquerque, New Mexico, April, 2025. Association for Computational Linguistics.
Soft Language Prompts for Language Transfer [link]Paper  abstract   bibtex   3 downloads  
Cross-lingual knowledge transfer, especially between high- and low-resource languages, remains challenging in natural language processing (NLP). This study offers insights for improving cross-lingual NLP applications through the combination of parameter-efficient fine-tuning methods. We systematically explore strategies for enhancing cross-lingual transfer through the incorporation of language-specific and task-specific adapters and soft prompts. We present a detailed investigation of various combinations of these methods, exploring their efficiency across 16 languages, focusing on 10 mid- and low-resource languages. We further present to our knowledge the first use of soft prompts for language transfer, a technique we call soft language prompts. Our findings demonstrate that in contrast to claims of previous work, a combination of language and task adapters does not always work best; instead, combining a soft language prompt with a task adapter outperforms most configurations in many cases.
@inproceedings{vykopalSoftLanguagePrompts2025,
	address = {Albuquerque, New Mexico},
	title = {Soft {Language} {Prompts} for {Language} {Transfer}},
	isbn = {979-8-89176-189-6},
	url = {https://aclanthology.org/2025.naacl-long.517/},
	abstract = {Cross-lingual knowledge transfer, especially between high- and low-resource languages, remains challenging in natural language processing (NLP). This study offers insights for improving cross-lingual NLP applications through the combination of parameter-efficient fine-tuning methods. We systematically explore strategies for enhancing cross-lingual transfer through the incorporation of language-specific and task-specific adapters and soft prompts. We present a detailed investigation of various combinations of these methods, exploring their efficiency across 16 languages, focusing on 10 mid- and low-resource languages. We further present to our knowledge the first use of soft prompts for language transfer, a technique we call soft language prompts. Our findings demonstrate that in contrast to claims of previous work, a combination of language and task adapters does not always work best; instead, combining a soft language prompt with a task adapter outperforms most configurations in many cases.},
	urldate = {2025-05-22},
	booktitle = {Proceedings of the 2025 {Conference} of the {Nations} of the {Americas} {Chapter} of the {Association} for {Computational} {Linguistics}: {Human} {Language} {Technologies} ({Volume} 1: {Long} {Papers})},
	publisher = {Association for Computational Linguistics},
	author = {Vykopal, Ivan and Ostermann, Simon and Simko, Marian},
	editor = {Chiruzzo, Luis and Ritter, Alan and Wang, Lu},
	month = apr,
	year = {2025},
	pages = {10294--10313},
}

Downloads: 3