论文标题
餐：稳定而积极的学习，以进行几次射击
MEAL: Stable and Active Learning for Few-Shot Prompting
论文作者
论文摘要
由于基础模型，通过启动和提示，很少有射击的分类取得了长足的进步，这是非常有效的少数学习者。但是，这种方法在不同的少数镜头（数据选择）和不同的芬特运行（运行变异性）之间具有很大的差异。这不仅是因为它阻碍了不同方法的公平比较，而且尤其是因为它使得很少的学习学习对于许多现实世界应用都不可靠。为了减轻这些问题，我们为更稳定和有效的几次学习做出了两项贡献：首先，我们提出了新颖的结合方法，并表明它们大大降低了运行的可变性。其次，我们引入了一种新的主动学习（AL）标准，以进行数据选择，并介绍了针对及时学习的第一个基于AL的方法。在我们的实验中，我们表明我们的组合方法，进餐（多碰撞填充和预测与主动学习结合），在五个不同的任务上提高了基于及时的芬太尼的整体性能。我们将在https://github.com/akoksal/meal中公开共享我们的代码和数据拆分。
Few-shot classification has made great strides due to foundation models that, through priming and prompting, are highly effective few-shot learners. However, this approach has high variance both across different sets of few shots (data selection) and across different finetuning runs (run variability). This is problematic not only because it impedes the fair comparison of different approaches, but especially because it makes few-shot learning too unreliable for many real-world applications. To alleviate these issues, we make two contributions for more stable and effective few-shot learning: First, we propose novel ensembling methods and show that they substantially reduce run variability. Second, we introduce a new active learning (AL) criterion for data selection and present the first AL-based approach specifically tailored towards prompt-based learning. In our experiments, we show that our combined method, MEAL (Multiprompt finetuning and prediction Ensembling with Active Learning), improves overall performance of prompt-based finetuning by 2.3 points on five diverse tasks. We publicly share our code and data splits in https://github.com/akoksal/MEAL.
