Adaptable and Reliable Text Classification using Large Language Models
This addresses text classification for NLP practitioners by simplifying workflows, but it is incremental as it builds on existing LLM capabilities.
The paper tackled text classification by introducing a system using Large Language Models (LLMs) as the core component, showing that certain LLMs surpass traditional methods in tasks like sentiment analysis and spam detection, with fine-tuning strategies making the model the top performer across all datasets.
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.