Self-Improving for Zero-Shot Named Entity Recognition with Large Language Models
This work addresses the problem of improving zero-shot NER performance for NLP practitioners, but it is incremental as it builds on existing LLM methods with a novel framework.
The paper tackles zero-shot named entity recognition with large language models by proposing a training-free self-improving framework that uses an unlabeled corpus to generate and select reliable self-annotations for in-context learning, achieving substantial performance improvements on four benchmarks.
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