Demonstration ordering, which is an important strategy for in-context learning (ICL), can significantly affects the performance of large language models (LLMs). However, most of the current approaches of ordering require additional knowledge and similarity calculation. We advocate the few-shot in-context curriculum learning (ICCL), a simple but effective demonstration ordering method for ICL, which implies gradually increasing the complexity of prompt demonstrations during the inference process. Then we design three experiments to discuss the effectiveness of ICCL, the formation mechanism of LLM's ICCL capability, and the impact of ordering subjects. Experimental results demonstrate that ICCL, developed during the instruction-tuning stage, is effective for open-source LLMs. Moreover, LLMs exhibit a weaker capacity compared to humans in discerning the difficulty levels of demonstrations. We release our code at https://github.com/61peng/curri_learning.

翻译：演示排序是上下文学习（ICL）中的一个重要策略，能显著影响大型语言模型（LLMs）的性能。然而，当前大多数排序方法需要额外的知识及相似度计算。我们提出少样本上下文课程学习（ICCL），这是一种简单而有效的ICL演示排序方法，其思想是在推理过程中逐步增加提示演示的复杂度。随后我们设计了三组实验，分别探讨ICCL的有效性、LLM的ICCL能力形成机制，以及排序对象的影响。实验结果表明，在指令微调阶段形成的ICCL对开源LLMs有效。此外，与人类相比，LLMs在识别演示难度层级方面的能力较弱。我们的代码已开源至https://github.com/61peng/curri_learning。