Adaptable and Reliable Text Classification using Large Language Models

TL;DR

This paper presents a new text classification approach using Large Language Models that is adaptable, reliable, and reduces preprocessing, with demonstrated superior performance across multiple NLP tasks and datasets.

Contribution

Introduces a flexible text classification system leveraging LLMs that simplifies workflows and enhances performance through few-shot and fine-tuning strategies.

Findings

LLMs outperform traditional methods in several NLP tasks

Fine-tuning improves LLM performance across datasets

System reduces preprocessing and domain expertise requirements

Abstract

Text classification is fundamental in Natural Language Processing (NLP), and the advent of Large Language Models (LLMs) has revolutionized the field. This paper introduces an adaptable and reliable text classification paradigm, which leverages LLMs as the core component to address text classification tasks. Our system simplifies the traditional text classification workflows, reducing the need for extensive preprocessing and domain-specific expertise to deliver adaptable and reliable text classification results. We evaluated the performance of several LLMs, machine learning algorithms, and neural network-based architectures on four diverse datasets. Results demonstrate that certain LLMs surpass traditional methods in sentiment analysis, spam SMS detection, and multi-label classification. Furthermore, it is shown that the system's performance can be further enhanced through few-shot or fine-tuning strategies, making the fine-tuned model the top performer across all datasets. Source code and datasets are available in this GitHub repository: https://github.com/yeyimilk/llm-zero-shot-classifiers.