llmNER: (Zero|Few)-Shot Named Entity Recognition, Exploiting the Power of Large Language Models

TL;DR

llmNER is a Python library that simplifies zero-shot and few-shot named entity recognition using large language models, enabling efficient prompt engineering and flexible application in NLP tasks.

Contribution

The paper introduces llmNER, a user-friendly library that streamlines prompt composition, querying, and parsing for LLM-based NER, facilitating research and practical use.

Findings

Validated on two NER tasks demonstrating flexibility

Enables efficient prompt engineering and testing

Removes barriers in in-context learning research

Abstract

Large language models (LLMs) allow us to generate high-quality human-like text. One interesting task in natural language processing (NLP) is named entity recognition (NER), which seeks to detect mentions of relevant information in documents. This paper presents llmNER, a Python library for implementing zero-shot and few-shot NER with LLMs; by providing an easy-to-use interface, llmNER can compose prompts, query the model, and parse the completion returned by the LLM. Also, the library enables the user to perform prompt engineering efficiently by providing a simple interface to test multiple variables. We validated our software on two NER tasks to show the library's flexibility. llmNER aims to push the boundaries of in-context learning research by removing the barrier of the prompting and parsing steps.