Adaptable and Reliable Text Classification using Large Language Models

Zhiqiang Wang, Yiran Pang, Yanbin Lin, Xingquan Zhu
5/17/2024
cs.CL

Official code: yeyimilk/llm-zero-shot-classifiers (39 stars, last commit 2024-05-30).

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.

View on arXivView PDF

Code Implementations(1)

yeyimilk/llm-zero-shot-classifiersOfficial100%

Large Language Models are zero-shot text classifiers; Smart Expert System: Large Language Models as Text Classifiers

394Shell, PythonNov 14, 20232 years ago
chatgptchatgpt4finetunellama3llm+2 more

Similar Papers

Text Classification in the LLM Era -- Where do we stand?

91% match2025

Large Language Models For Text Classification: Case Study And Comprehensive Review

88% match2025

Advancing Text Classification with Large Language Models and Neural Attention Mechanisms

87% match2025

LLM-as-classifier: Semi-Supervised, Iterative Framework for Hierarchical Text Classification using Large Language Models

87% match2025

Fine-tuning Large Language Models for Multigenerator, Multidomain, and Multilingual Machine-Generated Text Detection

87% match2024

Data Quality Enhancement on the Basis of Diversity with Large Language Models for Text Classification: Uncovered, Difficult, and Noisy

87% match2024

Cite this paper

@article{wang2024adaptable,
  title  = {Adaptable and Reliable Text Classification using Large Language Models},
  author = {Zhiqiang Wang and Yiran Pang and Yanbin Lin and Xingquan Zhu},
  year   = {2024},
  eprint = {2405.10523},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2405.10523v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2405.10523.svg)](https://codeofpaper.com/paper/2405.10523)

Discussion