Data annotation is the labeling or tagging of raw data with relevant information, essential for improving the efficacy of machine learning models. The process, however, is labor-intensive and expensive. The emergence of advanced Large Language Models (LLMs), exemplified by GPT-4, presents an unprecedented opportunity to revolutionize and automate the intricate process of data annotation. While existing surveys have extensively covered LLM architecture, training, and general applications, this paper uniquely focuses on their specific utility for data annotation. This survey contributes to three core aspects: LLM-Based Data Annotation, Assessing LLM-generated Annotations, and Learning with LLM-generated annotations. Furthermore, the paper includes an in-depth taxonomy of methodologies employing LLMs for data annotation, a comprehensive review of learning strategies for models incorporating LLM-generated annotations, and a detailed discussion on primary challenges and limitations associated with using LLMs for data annotation. As a key guide, this survey aims to direct researchers and practitioners in exploring the potential of the latest LLMs for data annotation, fostering future advancements in this critical domain. We provide a comprehensive papers list at \url{https://github.com/Zhen-Tan-dmml/LLM4Annotation.git}.

数据标注是提高机器学习模型效果的标记或标签化原始数据的过程，使用大型语言模型（LLMs）可以革新和自动化数据标注过程。本研究着重于LLM在数据标注中的特定用途，探讨了LLM基于数据标注、评估LLM生成的标注以及使用LLM生成的标注进行学习的方法。此外，还提供了LLM在数据标注中的方法学分类、包含LLM生成标注的模型的学习策略综述，并详细讨论了使用LLM进行数据标注所面临的主要挑战和限制。本文旨在为研究人员和从业者指导利用最新的LLMs进行数据标注，推动该关键领域的未来发展。

数据标注的大型语言模型调查