Let's Learn Step by Step: Enhancing In-Context Learning Ability with Curriculum Learning
This addresses the computational cost issue in ordering demonstrations for in-context learning, offering a practical improvement for researchers and practitioners using LLMs, though it is incremental.
The paper tackles the problem of demonstration ordering in in-context learning for large language models by proposing a curriculum learning method that gradually increases prompt complexity, showing effectiveness for open-source LLMs with experimental validation.
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 high computational costs to introduce the priori knowledge. In this paper, inspired by the human learning process, we propose a simple but effective demonstration ordering method for ICL, named the few-shot In-Context Curriculum Learning (ICCL). The ICCL implies gradually increasing the complexity of prompt demonstrations during the inference process. The difficulty can be assessed by human experts or LLMs-driven metrics, such as perplexity. Then we design extensive experiments to discuss the effectiveness of the ICCL at both corpus-level and instance-level. Moreover, we also investigate the formation mechanism of LLM's ICCL capability. Experimental results demonstrate that ICCL, developed during the instruction-tuning stage, is effective for representative open-source LLMs. To facilitate further research and applications by other scholars, we make the code publicly available.