Auto-ICL: In-Context Learning without Human Supervision
This addresses the labor-intensive and limiting nature of human supervision in in-context learning for large language models, offering a more scalable solution.
The paper tackles the problem of in-context learning requiring human-provided contexts by proposing an automatic framework for generating examples and instructions, resulting in model-generated contexts outperforming human-annotated ones like Few-Shot and Few-Shot-CoT, as well as surpassing self-generated methods such as Zero-CoT and Auto-CoT.
With in-context learning ability, the performance of large language models can be significantly boosted when provided with appropriate context. However, existing in-context learning methods mainly rely on human-provided contexts, such as labeled examples and explicit instructions. Writing context by humans is labor-intensive on various tasks and limits the model to tasks manageable by humans. To overcome these limitations, we propose Automatic In-Context Learning framework that enables the model to autonomously generate examples and instructions for problem-solving. With experiments across various models and datasets, results show that model-generated contexts outperform human-annotated contexts, including Few-Shot and Few-Shot-CoT methods, and surpass existing self-generated context methods like Zero-CoT and Auto-CoT.