用跨任务例子生成伪标签，低成本实现高效上下文学习。
From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning
- 先用跨任务例子引导大模型生成少量目标任务伪标签
- 通过图传播方法扩展标签，无需额外调用大模型
- 适合资源有限但需快速构建上下文学习示例的场景
上下文学习（ICL）使大语言模型（LLMs）能在不更新参数的情况下，仅通过几个输入输出示例完成新任务。然而，为新任务或难任务收集高质量示例成本高昂。本文提出一种低成本的两阶段流程：首先利用现成的跨任务示例引导LLM，对少量目标任务实例进行伪标注；随后引入基于图的标签传播方法，将标签信息扩散到剩余目标示例，无需额外调用LLM。由此生成的完整伪标签数据集用于构建任务内演示，支持上下文学习。该流程结合了跨任务监督的灵活性与无模型传播的可扩展性。在五个任务上的实验表明，该方法在显著降低标注成本的同时，仍能实现优异性能。
原文摘要 · Abstract (English)
The capability of in-context learning (ICL) enables large language models (LLMs) to perform novel tasks without parameter updates by conditioning on a few input-output examples. However, collecting high-quality examples for new or challenging tasks can be costly and labor-intensive. In this work, we propose a cost-efficient two-stage pipeline that reduces reliance on LLMs for data labeling. Our approach first leverages readily available cross-task examples to prompt an LLM and pseudo-label a small set of target task instances. We then introduce a graph-based label propagation method that spreads label information to the remaining target examples without additional LLM queries. The resulting fully pseudo-labeled dataset is used to construct in-task demonstrations for ICL. This pipeline combines the flexibility of cross-task supervision with the scalability of LLM-free propagation. Experiments across five tasks demonstrate that our method achieves strong performance while lowering labeling costs.
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。