让大模型在有错误标注的示范中仍能准确执行任务
In-Context Learning with Noisy Labels
- 设计新方法应对示范数据中的标签噪声问题
- 实验显示新方法可有效防止性能下降
- 适合关注真实场景下模型鲁棒性的研究者
上下文学习是指大型语言模型（LLMs）无需额外训练即可通过任务示范完成目标任务的新兴能力。近期研究通过选择更有效的示范来提升上下文学习性能，但忽略了现实世界中示范标签不可避免的噪声问题。本文提出新任务——带噪声标签的上下文学习，旨在解决示范标签被污染时的真实世界挑战。受噪声标签学习研究启发，我们提出新方法及基线方法。实验表明，所提方法能有效防护由标签噪声引发的性能退化。
原文摘要 · Abstract (English)
In-context learning refers to the emerging ability of large language models (LLMs) to perform a target task without additional training, utilizing demonstrations of the task. Recent studies aim to enhance in-context learning performance by selecting more useful demonstrations. However, they overlook the presence of inevitable noisy labels in task demonstrations that arise during the labeling process in the real-world. In this paper, we propose a new task, in-context learning with noisy labels, which aims to solve real-world problems for in-context learning where labels in task demonstrations would be corrupted. Moreover, we propose a new method and baseline methods for the new task, inspired by studies in learning with noisy labels. Through experiments, we demonstrate that our proposed method can serve as a safeguard against performance degradation in in-context learning caused by noisy labels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。