Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning

arXiv:2402.10738v1 Announce Type: new
Abstract: 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 …

arxiv context cs.cl curriculum curriculum learning in-context learning learn type