Adapting large language models (LLMs) to new languages is an expensive and opaque process. Understanding how language models acquire new languages and multilingual abilities is key to achieve efficient adaptation. Prior work on multilingual interpretability research focuses primarily on how trained models process multilingual instructions, leaving unexplored the mechanisms through which they acquire new languages during training. We investigate these training dynamics on decoder-only transformers through the lens of two functional cognitive specializations: language perception (input comprehension) and production (output generation). Through experiments on low-resource languages, we demonstrate how perceptual and productive specialization emerges in different regions of a language model by running layer ablation sweeps from the model's input and output directions. Based on the observed specialization patterns, we propose CogSym, a layer-wise heuristic that enables effective adaptation by exclusively fine-tuning a few early and late layers. We show that tuning only the 25% outermost layers achieves downstream task performance within 2-3% deviation from the full fine-tuning baseline. CogSym yields consistent performance with adapter methods such as LoRA, showcasing generalization beyond full fine-tuning. These findings provide insights to better understand how LLMs learn new languages and push toward accessible and inclusive language modeling.

翻译：将大语言模型（LLMs）适配至新语言是一个昂贵且不透明的过程。理解语言模型如何习得新语言及多语言能力，是实现高效适配的关键。先前关于多语言可解释性的研究主要聚焦于已训练模型如何理解多语言指令，而未探索其在训练过程中获取新语言的机制。我们从两种功能性认知特化——语言感知（输入理解）与语言生成（输出产生）的视角，探究仅解码器Transformer架构中的训练动态。通过对低资源语言的实验，我们沿模型的输入与输出方向进行逐层消融扫描，揭示了感知与生成特化如何在语言模型的不同区域涌现。基于观测到的特化模式，我们提出逐层启发式方法CogSym，该方法通过仅微调少数初始层与末尾层实现高效适配。实验表明，仅调整25%的边缘层即可在下游任务中达到与全参数微调基线相差2-3%的性能。CogSym与LoRA等适配器方法表现一致，展现了超越全参数微调的泛化能力。这些发现为理解大语言模型如何习得新语言提供了洞见，并推动了可及且包容的语言建模研究。