PromptNER: Prompting For Named Entity Recognition

TL;DR

PromptNER leverages prompt-based techniques with large language models to achieve state-of-the-art results in few-shot and cross-domain Named Entity Recognition, significantly outperforming existing methods.

Contribution

Introduces PromptNER, a novel prompt-based algorithm that enhances few-shot and cross-domain NER performance using entity definitions and LLM-generated explanations.

Findings

Achieves 4-9% absolute F1 score improvements on standard NER datasets.

Sets new benchmarks on 3 out of 5 cross-domain NER tasks.

Operates effectively with less than 2% of the data used by previous methods.

Abstract

In a surprising turn, Large Language Models (LLMs) together with a growing arsenal of prompt-based heuristics now offer powerful off-the-shelf approaches providing few-shot solutions to myriad classic NLP problems. However, despite promising early results, these LLM-based few-shot methods remain far from the state of the art in Named Entity Recognition (NER), where prevailing methods include learning representations via end-to-end structural understanding and fine-tuning on standard labeled corpora. In this paper, we introduce PromptNER, a new state-of-the-art algorithm for few-Shot and cross-domain NER. To adapt to any new NER task PromptNER requires a set of entity definitions in addition to the standard few-shot examples. Given a sentence, PromptNER prompts an LLM to produce a list of potential entities along with corresponding explanations justifying their compatibility with the provided entity type definitions. Remarkably, PromptNER achieves state-of-the-art performance on few-shot NER, achieving a 4% (absolute) improvement in F1 score on the ConLL dataset, a 9% (absolute) improvement on the GENIA dataset, and a 4% (absolute) improvement on the FewNERD dataset. PromptNER also moves the state of the art on Cross Domain NER, outperforming prior methods (including those not limited to the few-shot setting), setting a new mark on 3/5 CrossNER target domains, with an average F1 gain of 3%, despite using less than 2% of the available data.