Exploring the application of powerful large language models (LLMs) on the named entity recognition (NER) task has drawn much attention recently. This work pushes the performance boundary of zero-shot NER with LLMs by proposing a training-free self-improving framework, which utilizes an unlabeled corpus to stimulate the self-learning ability of LLMs. First, we use the LLM to make predictions on the unlabeled corpus using self-consistency and obtain a self-annotated dataset. Second, we explore various strategies to select reliable annotations to form a reliable self-annotated dataset. Finally, for each test input, we retrieve demonstrations from the reliable self-annotated dataset and perform inference via in-context learning. Experiments on four benchmarks show substantial performance improvements achieved by our framework. Through comprehensive experimental analysis, we find that increasing the size of unlabeled corpus or iterations of self-improving does not guarantee further improvement, but the performance might be boosted via more advanced strategies for reliable annotation selection. Code and data are publicly available at https://github.com/Emma1066/Self-Improve-Zero-Shot-NER

翻译：探索强大的大语言模型（LLMs）在命名实体识别（NER）任务中的应用近期引起了广泛关注。本文通过提出一种无需训练的自改进框架，利用无标注语料库激发大语言模型的自学习能力，进一步提升了LLMs在零样本NER任务中的性能边界。首先，我们利用LLM通过自一致性方法对无标注语料库进行预测，获得自标注数据集。其次，我们探索多种策略筛选可靠标注结果，构建高质量的自标注数据集。最后，针对每个测试输入，我们从可靠自标注数据集中检索示范样本，通过上下文学习执行推理。在四个基准数据集上的实验表明，我们的框架实现了显著的性能提升。通过全面的实验分析发现，增加无标注语料库规模或自改进迭代次数并不保证性能持续提升，但采用更先进的可靠标注选择策略可能带来性能突破。相关代码与数据已在https://github.com/Emma1066/Self-Improve-Zero-Shot-NER 公开。