Despite recent explosion of interests in in-context learning, the underlying mechanism and the precise impact of the quality of demonstrations remain elusive. Intuitively, ground-truth labels should have as much impact in in-context learning (ICL) as supervised learning, but recent work reported that the input-label correspondence is significantly less important than previously thought. Intrigued by this counter-intuitive observation, we re-examine the importance of ground-truth labels in in-context learning. With the introduction of two novel metrics, namely Label-Correctness Sensitivity and Ground-truth Label Effect Ratio (GLER), we were able to conduct quantifiable analysis on the impact of ground-truth label demonstrations. Through extensive analyses, we find that the correct input-label mappings can have varying impacts on the downstream in-context learning performances, depending on the experimental configuration. Through additional studies, we identify key components, such as the verbosity of prompt templates and the language model size, as the controlling factor to achieve more noise-resilient ICL.
翻译:尽管最近对文中学习的兴趣激增,但基本机制和示威质量的确切影响仍然难以捉摸。 诚然,地面真实标签应该像监督的学习一样对文中学习产生同样大的影响,但最近的工作报告说,输入标签的通信远不如以前想象的那么重要。我们从这一反直觉观察中重新审视了地面真实标签在文中学习的重要性。随着引入了两种新型指标,即Label-更正感知性和地面真实性拉贝尔效果比率(GLER),我们得以对地面真实性标签演示的影响进行量化分析。通过广泛的分析,我们发现正确的输入标签制图可能对下游的文中学习表现产生不同的影响,这取决于实验性结构。我们通过进一步的研究,我们确定了关键组成部分,如迅速的模板和语言模型大小等,作为实现更耐噪音的ICLOC的控制因素。