摘要
This survey paper investigates how personalized learning offered by Large Language Models (LLMs) could transform educational experiences. We explore Knowledge Editing Techniques (KME), which guarantee that LLMs maintain current knowledge and are essential for providing accurate and up-to-date information. The datasets analyzed in this article are intended to evaluate LLM performance on educational tasks, such as error correction and question answering. We acknowledge the limitations of LLMs while highlighting their fundamental educational capabilities in writing, math, programming, and reasoning. We also explore two promising system architectures: a Mixture-of-Experts (MoE) framework and a unified LLM approach, for LLM-based education. The MoE approach makes use of specialized LLMs under the direction of a central controller for various subjects. We also discuss the use of LLMs for individualized feedback and their possibility in content creation, including the creation of videos, quizzes, and plans. In our final section, we discuss the difficulties and potential solutions for incorporating LLMs into educational systems, highlighting the importance of factual accuracy, reducing bias, and fostering critical thinking abilities. The purpose of this survey is to show the promise of LLMs as well as the issues that still need to be resolved in order to facilitate their responsible and successful integration into the educational ecosystem.
This survey paper investigates how personalized learning offered by Large Language Models (LLMs) could transform educational experiences. We explore Knowledge Editing Techniques (KME), which guarantee that LLMs maintain current knowledge and are essential for providing accurate and up-to-date information. The datasets analyzed in this article are intended to evaluate LLM performance on educational tasks, such as error correction and question answering. We acknowledge the limitations of LLMs while highlighting their fundamental educational capabilities in writing, math, programming, and reasoning. We also explore two promising system architectures: a Mixture-of-Experts (MoE) framework and a unified LLM approach, for LLM-based education. The MoE approach makes use of specialized LLMs under the direction of a central controller for various subjects. We also discuss the use of LLMs for individualized feedback and their possibility in content creation, including the creation of videos, quizzes, and plans. In our final section, we discuss the difficulties and potential solutions for incorporating LLMs into educational systems, highlighting the importance of factual accuracy, reducing bias, and fostering critical thinking abilities. The purpose of this survey is to show the promise of LLMs as well as the issues that still need to be resolved in order to facilitate their responsible and successful integration into the educational ecosystem.
