{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/adapters-for-altering-llm-vocabularies-what","title":"Adapters for Altering LLM Vocabularies: What Languages Benefit the Most?","arxiv_id":"2410.09644","date":"2024-10-12","proceeding":null,"authors":["Hyojung Han","Akiko Eriguchi","Haoran Xu","Hieu Hoang","Marine Carpuat","Huda Khayrallah"],"abstract":"Vocabulary adaptation, which integrates new vocabulary into pre-trained language models (LMs), enables expansion to new languages and mitigates token over-fragmentation. However, existing approaches are limited by their reliance on heuristic or external embeddings. We propose VocADT, a novel method for vocabulary adaptation using adapter modules that are trained to learn the optimal linear combination of existing embeddings while keeping the model's weights fixed. VocADT offers a flexible and scalable solution without requiring external resources or language constraints. Across 11 languages-with various scripts, resource availability, and fragmentation-we demonstrate that VocADT outperforms the original Mistral model and other baselines across various multilingual tasks. We find that Latin-script languages and highly fragmented languages benefit the most from vocabulary adaptation. We further fine-tune the adapted model on the generative task of machine translation and find that vocabulary adaptation is still beneficial after fine-tuning and that VocADT is the most effective method.","url_abs":"https://arxiv.org/abs/2410.09644v1","url_pdf":"https://arxiv.org/pdf/2410.09644v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"adapters-for-altering-llm-vocabularies-what","repo_url":"https://github.com/h-j-han/VocADT","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"}],"methods":[{"method_slug":"adapter","method_name":"Adapter"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.09644","atlas_url":"https://app.syntology.ai/?focus=2410.09644","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}