Smart Expert System: Large Language Models as Text Classifiers

• DOI: 10.48550/arxiv.2405.10523
• Publication Date: 2024-05-17
• Authors: Zhiqiang Wang; Yiran Pang; Yanbin Lin
• Keywords: FOS: Computer and information sciences; Computer Science - Computation and Language; Computation and Language (cs.CL)

Text classification is a fundamental task in Natural Language Processing (NLP), and the advent of Large Models (LLMs) has revolutionized field. This paper introduces Smart Expert System, novel approach that leverages LLMs as text classifiers. The system simplifies traditional workflow, eliminating need for extensive preprocessing domain expertise. performance several LLMs, machine learning (ML) algorithms, neural network (NN) based structures evaluated on four datasets. Results demonstrate certain surpass methods sentiment analysis, spam SMS detection multi-label classification. Furthermore, it shown system's can be further enhanced through few-shot or fine-tuning strategies, making fine-tuned model top performer across all Source code datasets are available this GitHub repository: https://github.com/yeyimilk/llm-zero-shot-classifiers.