{"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/monolingual-or-multilingual-instruction","title":"Monolingual or Multilingual Instruction Tuning: Which Makes a Better Alpaca","arxiv_id":"2309.08958","date":"2023-09-16","proceeding":null,"authors":["Pinzhen Chen","Shaoxiong Ji","Nikolay Bogoychev","Andrey Kutuzov","Barry Haddow","Kenneth Heafield"],"abstract":"Foundational large language models (LLMs) can be instruction-tuned to perform open-domain question answering, facilitating applications like chat assistants. While such efforts are often carried out in a single language, we empirically analyze cost-efficient strategies for multilingual scenarios. Our study employs the Alpaca dataset and machine translations of it to form multilingual data, which is then used to tune LLMs through either low-rank adaptation or full-parameter training. Under a controlled computation budget, comparisons show that multilingual tuning is on par or better than tuning a model for each language. Furthermore, multilingual tuning with downsampled data can be as powerful and more robust. Our findings serve as a guide for expanding language support through instruction tuning.","url_abs":"https://arxiv.org/abs/2309.08958v2","url_pdf":"https://arxiv.org/pdf/2309.08958v2.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":"monolingual-or-multilingual-instruction","repo_url":"https://github.com/hplt-project/monolingual-multilingual-instruction-tuning","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"},{"task_slug":"large-language-model","task_name":"Large Language Model"},{"task_slug":"multilingual-nlp","task_name":"Multilingual NLP"},{"task_slug":"open-domain-question-answering","task_name":"Open-Domain Question Answering"},{"task_slug":"open-question","task_name":"Open-Ended Question Answering"},{"task_slug":"question-answering","task_name":"Question Answering"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2309.08958","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}