In this study, we reveal an in-context learning (ICL) capability of multilingual large language models (LLMs): by translating the input to several languages, we provide Parallel Input in Multiple Languages (PiM) to LLMs, which significantly enhances their comprehension abilities. To test this capability, we design extensive experiments encompassing 8 typical datasets, 7 languages and 8 state-of-the-art multilingual LLMs. Experimental results show that (1) incorporating more languages help PiM surpass the conventional ICL further; (2) even combining with the translations that are inferior to baseline performance can also help. Moreover, by examining the activated neurons in LLMs, we discover a counterintuitive but interesting phenomenon. Contrary to the common thought that PiM would activate more neurons than monolingual input to leverage knowledge learned from diverse languages, PiM actually inhibits neurons and promotes more precise neuron activation especially when more languages are added. This phenomenon aligns with the neuroscience insight about synaptic pruning, which removes less used neural connections, strengthens remainders, and then enhances brain intelligence.

翻译：在本研究中，我们揭示了多语言大语言模型（LLMs）的一种上下文学习（ICL）能力：通过将输入翻译成多种语言，我们为LLMs提供了多语言并行输入（PiM），这显著增强了它们的理解能力。为测试这一能力，我们设计了涵盖8个典型数据集、7种语言和8个最先进多语言LLMs的广泛实验。实验结果表明：（1）纳入更多语言有助于PiM进一步超越传统ICL；（2）即使结合表现劣于基线的翻译也能带来帮助。此外，通过检查LLMs中激活的神经元，我们发现了一个反直觉但有趣的现象。与普遍认为PiM会激活比单语言输入更多神经元以利用从不同语言中学到的知识相反，PiM实际上抑制了神经元活动，并促进了更精确的神经元激活，尤其是在添加更多语言时。这一现象与神经科学中关于突触修剪的观点一致——突触修剪会移除较少使用的神经连接，强化剩余连接，进而增强大脑智能。