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 this https URL

演示排序是上下文学习中的重要策略，对大型语言模型的性能有显著影响。我们提出了少样本上下文课程学习（ICCL），一种简单但有效的演示排序方法，其在推理过程中逐渐增加提示演示的复杂性。通过设计三个实验来探讨 ICCL 的有效性、LLM 的 ICCL 能力形成机制以及排序主题的影响，实验结果表明，ICCL 在指导调整阶段对开源 LLM 有效。此外，与人类相比，LLM 对演示的难度层次辨别能力较弱。我们在此 https URL 上发布了我们的代码。