MEAL：面向少样本提示的稳定与主动学习
MEAL: Stable and Active Learning for Few-Shot Prompting
AI总结：
针对少样本提示学习中数据选择和微调运行的高方差问题，提出集成方法降低运行变异性并引入首个针对提示学习的主动学习准则，组合方法MEAL在五个任务上提升性能2.3个百分点。
摘要：
少样本分类取得了巨大进展，这得益于基础模型通过启动和提示成为了高效的少样本学习器。然而，这种方法在不同的少样本集合（数据选择）和不同的微调运行（运行变异性）之间都具有高方差。这不仅阻碍了不同方法的公平比较，尤其使得少样本学习在许多实际应用中过于不可靠。为缓解这些问题，我们在更稳定和有效的少样本学习方面做出了两项贡献：首先，我们提出了新颖的集成方法，并表明它们显著降低了运行变异性。其次，我们引入了一种用于数据选择的新主动学习（AL）准则，并提出了首个专门针对基于提示的学习定制的AL方法。在实验中，我们展示了我们的组合方法MEAL（基于主动学习的多提示微调与预测集成）在五个不同的任务上将基于提示的微调整体性能提高了2.3个百分点。我们在 https://github.com/akoksal/MEAL 公开分享我们的代码和数据划分。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
