A Survey of the Applications of Large Language Models in the Educational Sector

The popularity of large language models (LLMs) such as Generative Pre-Trained Transformer (GPT), Gemini, and Llama, has soared in recent years due to its wide range of applications in fields such as education, medicine, law, and software development. Despite their numerous potential applications and benefits, the ease of access and ability of LLMs to produce human-like text has led to concerns, such plagiarism and cheating, about their use in education. In this study, a survey of recent literature, that discusses the advantages and disadvantages of the use of LLMs in an educational setting, has been performed, and two use cases have been explored. This work aims to provide a clear picture of the potential pitfalls of integrating LLMs in education and possible mitigation strategies. The survey found that existing teaching and assessment practices must be updated to accommodate the use of LLMs in education, as they are crucial due to their various advantages such as reducing student and teacher workload, increasing accessibility, and promoting creativity and engagement.