Sub-SA：通过子模选择性标注强化上下文学习
Sub-SA: Strengthen In-context Learning via Submodular Selective Annotation
AI总结：
针对大语言模型上下文学习中提示选择标注成本高的问题，提出基于子模的Sub-SA选择性标注方法，结合RPR奖惩正则化平衡数据多样性与代表性，通过贪心搜索高效选样，降低成本并提升上下文示例质量。
摘要：
上下文学习（ICL）利用上下文示例作为提示来支持大语言模型（LLM）的预测，这些提示对实现优异性能起着关键作用。然而，从大量标注示例池中选择合适的提示往往需要高昂的标注成本。为解决这一挑战，我们提出了Sub-SA（子模选择性标注），这是一种基于子模的选择性标注方法。Sub-SA的目标是降低标注成本，同时提升上下文示例的质量，并最小化选择过程的时间消耗。在Sub-SA中，我们设计了一个子模函数，可有效辅助待标注子集的选择，并从理论角度证明了其单调性和子模性特征。具体而言，我们提出了RPR（奖惩正则化），分别通过奖励项和惩罚项更好地平衡未标注数据集的多样性与代表性。由此，待标注选择问题可通过基于该子模函数的简单且高效的贪心搜索算法有效解决。最后，我们应用相似性提示检索来获取ICL所需的示例。
英文摘要：
In-context learning (ICL) leverages in-context examples as prompts for the predictions of Large Language Models (LLMs). These prompts play a crucial role in achieving strong performance. However, the selection of suitable prompts from a large pool of labeled examples often entails significant annotation costs. To address this challenge, we propose Sub-SA (Submodular Selective Annotation), a submodule-based selective annotation method. The aim of Sub-SA is to reduce annotation costs while improving the quality of in-context examples and minimizing the time consumption of the selection process. In Sub-SA, we design a submodular function that facilitates effective subset selection for annotation and demonstrates the characteristics of monotonically and submodularity from the theoretical perspective. Specifically, we propose RPR (Reward and Penalty Regularization) to better balance the diversity and representativeness of the unlabeled dataset attributed to a reward term and a penalty term, respectively. Consequently, the selection for annotations can be effectively addressed with a simple yet effective greedy search algorithm based on the submodular function. Finally, we apply the similarity prompt retrieval to get the examples for ICL.
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。
