Additionally, the strong dependency among in-context examples makes it an NP-hard combinatorial optimization problem and enumerating all permutations is infeasible. Hence we propose LENS, a fiLter-thEN-Search method to tackle this challenge in two stages: First we filter the dataset to obtain informative in-context examples individually. Specifically, we propose a novel metric, InfoScore, to evaluate the example's in-context informativeness based on the language model's feedback, and further propose a progressive filtering process to filter out uninformative examples. Then we propose diversity-guided example search which iteratively refines and evaluates the selected example permutations, to find examples that fully depict the task. The experimental results show that LENS significantly outperforms a wide range of baselines.

翻译：此外，上下文示例间的强依赖性使其成为NP难组合优化问题，枚举所有排列不可行。因此，我们提出LENS方法（一种过滤再搜索的方法），分两阶段应对这一挑战：首先过滤数据集，逐一获取信息量丰富的上下文示例。具体而言，我们提出新指标InfoScore，基于语言模型的反馈评估示例的上下文信息量，并进一步提出渐进式过滤过程，剔除信息量低的示例。随后，我们提出多样性引导的示例搜索方法，通过迭代优化并评估所选示例排列，找到能充分描述任务的示例。实验结果表明，LENS显著优于多种基线方法。