Language models, especially pre-trained large language models, have showcased remarkable abilities as few-shot in-context learners (ICL), adept at adapting to new tasks with just a few demonstrations in the input context. However, the model's ability to perform ICL is sensitive to the choice of the few-shot demonstrations. Instead of using a fixed set of demonstrations, one recent development is to retrieve demonstrations tailored to each input query. The implementation of demonstration retrieval is relatively straightforward, leveraging existing databases and retrieval systems. This not only improves the efficiency and scalability of the learning process but also has been shown to reduce biases inherent in manual example selection. In light of the encouraging results and growing research in ICL with retrieved demonstrations, we conduct an extensive review of studies in this area. In this survey, we discuss and compare different design choices for retrieval models, retrieval training procedures, and inference algorithms.

翻译：语言模型，尤其是预训练大规模语言模型，已展现出作为小样本上下文学习器（ICL）的显著能力，能够仅凭借输入上下文中的少量示例就适应新任务。然而，模型执行ICL的能力对少样本示例的选择十分敏感。为克服使用固定示例集的局限，最新进展之一是根据每个输入查询检索定制化的示例。这种示例检索的实现相对直接，可利用现有数据库和检索系统来完成。这不仅提升了学习过程的效率和可扩展性，还被证明能减少人工选择示例时固有的偏差。鉴于基于检索示例的上下文学习（ICL）取得的鼓舞性成果及日益增多的研究，我们对这一领域进行了全面综述。在本综述中，我们探讨并比较了检索模型的不同设计选择、检索训练流程以及推理算法。