Open and Distance Learning (ODL) is a mode of providing flexible educational opportunities at their doorsteps both in terms of access and multiple modes of acquiring knowledge. In Open and Distance Learning (ODL) institutions it is difficult to offer timely and effective support to students as there is no regular modes of classes, there is no regular contact or communication with the students and there is physical separation between students and teachers. Open and Distance Learning (ODL) systems…
Read moreOpen and Distance Learning (ODL) is a mode of providing flexible educational opportunities at their doorsteps both in terms of access and multiple modes of acquiring knowledge. In Open and Distance Learning (ODL) institutions it is difficult to offer timely and effective support to students as there is no regular modes of classes, there is no regular contact or communication with the students and there is physical separation between students and teachers. Open and Distance Learning (ODL) systems facing huge challenges of delivering timely and effective student support services over different geographical areas. The Universities working on ODL mode of education is dependent on human and machine interactions since there is no continuous classroom teaching-learning process involved, the application of the Artificial Intelligence fills the gap between the Students and Teachers. With the integration of Artificial Intelligence using Deep Learning and Machine Learning algorithms provide different applications in ODL such as giving continous feedback to the Students, shifting learning platform according to need of the students, automated arrangements of classes, evaluation of the assignments, checking plagiarism, assist students in adopting productive and qualitative learning behaviour. The incorporation of Large Language Models (LLMs) can solve these issues by automating student query responses, thus improving the learning process. The emergence of Large Language Models (LLMs) like GPT-4 has opened up new possibilities for the automation of student query management. This paper suggests an integrated proposed framework that incorporates LLMs into ODL environments to automatically process and respond to student queries. The framework aims to ensure precision, customization and scalability with human-in-the-loop control capabilities for ensuring quality. The present paper formulates a framework for designing an LLM-based system for addressing student questions in ODL. The paper involves a review of the literature, elaborated system design, implementation considerations and conceptual flow diagrams.
