InstructAlign: High-and-Low Resource Language Alignment via Continual Crosslingual Instruction Tuning
This work addresses the challenge of improving language model performance for underrepresented languages, which is an incremental advancement in language adaptation methods.
The paper tackles the problem of adapting instruction-tuned large language models to low-resource languages without causing catastrophic forgetting, achieving effective language alignment with limited parallel data.
Large language models (LLMs) that are tuned with instructions have demonstrated remarkable capabilities in various tasks and languages. However, their ability to generalize to underrepresented languages is limited due to the scarcity of available data. Additionally, directly adapting new languages to instruction-tuned LLMs can result in catastrophic forgetting, which leads to the loss of multitasking ability. To address this issue, we propose InstructAlign which uses continual crosslingual instruction tuning to enable LLMs to align new unseen languages with previously learned high-resource languages. Our results demonstrate the effectiveness of InstructAlign in enabling the model to understand low-resource languages with limited parallel data while preventing catastrophic forgetting. Our work contributes to the advancement of language adaptation methods, particularly for adapting instruction-tuned LLMs to underrepresented languages. Our code is released on https://github.com/HLTCHKUST/InstructAlign