Evaluating Named Entity Recognition Using Few-Shot Prompting with Large Language Models

TL;DR

This paper assesses the effectiveness of few-shot prompting with large language models like GPT-4 for Named Entity Recognition, highlighting their ability to adapt to new entities with minimal data and exploring factors influencing performance.

Contribution

It provides a comprehensive evaluation of large language models' few-shot NER capabilities, comparing them to traditional methods and analyzing prompt engineering effects.

Findings

Large models perform well with limited data

Prompt engineering significantly impacts results

Models adapt to new domains and entity types

Abstract

This paper evaluates Few-Shot Prompting with Large Language Models for Named Entity Recognition (NER). Traditional NER systems rely on extensive labeled datasets, which are costly and time-consuming to obtain. Few-Shot Prompting or in-context learning enables models to recognize entities with minimal examples. We assess state-of-the-art models like GPT-4 in NER tasks, comparing their few-shot performance to fully supervised benchmarks. Results show that while there is a performance gap, large models excel in adapting to new entity types and domains with very limited data. We also explore the effects of prompt engineering, guided output format and context length on performance. This study underscores Few-Shot Learning's potential to reduce the need for large labeled datasets, enhancing NER scalability and accessibility.