InstructionCP: A Simple yet Effective Approach for Transferring Large Language Models to Target Languages

The rapid development of large language models (LLMs) in recent years has largely focused on English, resulting in models that respond exclusively in English.To adapt these models to other languages, continual pre-training (CP) is often employed, followed by supervised fine-tuning (SFT) to maintain conversational abilities.However, CP and SFT can reduce a model's ability to filter harmful content.We propose Instruction Continual Pre-training (In-sCP), which integrates instruction tags-also known as chat templates-into the CP process to prevent loss of conversational proficiency while acquiring new languages.Empirical evaluations on language alignment, reliability, and knowledge benchmarks confirm the efficacy of InsCP.Notably, this approach requires only 0.1 billion tokens of high-quality instructionfollowing data, thereby reducing resource consumption.