{"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/bactrian-x-a-multilingual-replicable","title":"Bactrian-X: Multilingual Replicable Instruction-Following Models with Low-Rank Adaptation","arxiv_id":"2305.15011","date":"2023-05-24","proceeding":null,"authors":["Haonan Li","Fajri Koto","Minghao Wu","Alham Fikri Aji","Timothy Baldwin"],"abstract":"Instruction tuning has shown great promise in improving the performance of large language models. However, research on multilingual instruction tuning has been limited due to the scarcity of high-quality instruction-response datasets across different languages. To bridge this gap, we present Bactrian-X, a comprehensive multilingual parallel dataset of 3.4 million instruction-response pairs across 52 languages. Leveraging this dataset, we train a set of adapters using low-rank adaptation (LoRA), which are lightweight components that seamlessly integrate with large language models. These adapters have a substantially lower parameter count than the base model, making them easily replaceable and usable as plug-ins for different languages or language groups. Extensive experiments in various multilingual evaluation settings demonstrate that models derived from LoRA-based training over Bactrian-X outperform both the vanilla models and existing instruction-tuned models. The code and models are publicly available at https://github.com/mbzuai-nlp/bactrian-x","url_abs":"https://arxiv.org/abs/2305.15011v2","url_pdf":"https://arxiv.org/pdf/2305.15011v2.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":"bactrian-x-a-multilingual-replicable","repo_url":"https://github.com/mbzuai-nlp/bactrian-x","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[{"slug":"bactrian-x","name":"Bactrian-X","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.15011","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}