用伪标签提升大模型少样本学习能力，降低标注成本。
MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning
- 基于影响度筛选关键无标签数据，生成伪标签。
- 在测试时自适应选择伪标签，提升多示例学习性能。
- 适合标注稀缺场景下的大模型应用。
上下文学习（ICL）使大语言模型（LLMs）通过在输入中加入多个输入-输出示例（即示范）来处理多样化任务。近年来，随着大语言模型上下文窗口的扩展，多示例ICL（使用数百个示范）已超越少示例ICL（依赖少量示范）。然而，该方法常受限于大规模标注数据的高成本。为此，我们提出一种新的影响驱动型多示例ICL框架——MAPLE（Many-Shot Adaptive Pseudo-LabEling），利用伪标签弥补标签信息不足。首先识别出具有影响力的无标签样本，并通过查询大模型为其生成伪标签；随后，将这些伪标签样本自适应地选为每个测试查询的输入，从而提升多示例ICL性能，且几乎不增加标注成本。在真实数据集上的大量实验表明，该框架能有效增强大模型在有限标注数据下的适应性与表现。
原文摘要 · Abstract (English)
In-Context Learning (ICL) empowers Large Language Models (LLMs) to tackle diverse tasks by incorporating multiple input-output examples, known as demonstrations, into the input of LLMs. More recently, advancements in the expanded context windows of LLMs have led to many-shot ICL, which uses hundreds of demonstrations and outperforms few-shot ICL, which relies on fewer examples. However, this approach is often hindered by the high cost of obtaining large amounts of labeled data. To address this challenge, we propose Many-Shot Adaptive Pseudo-LabEling, namely MAPLE, a novel influence-based many-shot ICL framework that utilizes pseudo-labeled samples to compensate for the lack of label information. We first identify a subset of impactful unlabeled samples and perform pseudo-labeling on them by querying LLMs. These pseudo-labeled samples are then adaptively selected and tailored to each test query as input to improve the performance of many-shot ICL, without significant labeling costs. Extensive experiments on real-world datasets demonstrate the effectiveness of our framework, showcasing its ability to enhance LLM adaptability and performance with limited labeled data.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。