Despite the significant improvements achieved by large language models (LLMs) in English reasoning tasks, these models continue to struggle with multilingual reasoning. Recent studies leverage a full-parameter and two-stage training paradigm to teach models to first understand non-English questions and then reason. However, this method suffers from both substantial computational resource computing and catastrophic forgetting. The fundamental cause is that, with the primary goal of enhancing multilingual comprehension, an excessive number of irrelevant layers and parameters are tuned during the first stage. Given our findings that the representation learning of languages is merely conducted in lower-level layers, we propose an efficient multilingual reasoning alignment approach that precisely identifies and fine-tunes the layers responsible for handling multilingualism. Experimental results show that our method, SLAM, only tunes 6 layers' feed-forward sub-layers including 6.5-8% of all parameters within 7B and 13B LLMs, achieving superior average performance than all strong baselines across 10 languages. Meanwhile, SLAM only involves one training stage, reducing training time by 4.1-11.9 compared to the two-stage method.

本研究针对大型语言模型在多语言推理方面的不足，提出了一种高效的多语言推理对齐方法SLAM。该方法通过精确识别和微调处理多语言性的层，解决了过度调优导致的计算资源浪费和灾难性遗忘问题。实验结果表明，SLAM在10种语言上表现优于所有强基线，训练时间比传统的两阶段方法减少了4.1-11.9倍。

SLAM：通过选择性语言对齐实现高效多语言推理