Scholarlink

This review examines how LLMs, particularly those using transformer architectures, have addressed persistent challenges in text classification through their advanced context understanding and generative capabilities. Despite significant progress, the review highlights gaps in current research, such as the need for greater transparency, reduced computational cost, and better management of model hallucinations. The paper concludes with recommendations for future research to improve the use of LLMs in content classification and ensure their effective use in various domains.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

A Systematic Literature Review on LLM-Based Content Classification

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Diogo Cosme,
  • António Galvão,
  • Fernando Brito e Abreu

摘要

This review examines how LLMs, particularly those using transformer architectures, have addressed persistent challenges in text classification through their advanced context understanding and generative capabilities. Despite significant progress, the review highlights gaps in current research, such as the need for greater transparency, reduced computational cost, and better management of model hallucinations. The paper concludes with recommendations for future research to improve the use of LLMs in content classification and ensure their effective use in various domains.