ChatEd: A Chatbot Leveraging ChatGPT for an Enhanced Learning Experience in Higher Education
This work addresses the problem of unreliable AI responses for students in higher education, but it is incremental as it builds on existing chatbot and LLM methods.
The paper tackles the challenge of deploying ChatGPT in higher education by combining it with an information retrieval chatbot framework to reduce incorrect or biased answers, showing high promise in empirical evaluations.
With the rapid evolution of Natural Language Processing (NLP), Large Language Models (LLMs) like ChatGPT have emerged as powerful tools capable of transforming various sectors. Their vast knowledge base and dynamic interaction capabilities represent significant potential in improving education by operating as a personalized assistant. However, the possibility of generating incorrect, biased, or unhelpful answers are a key challenge to resolve when deploying LLMs in an education context. This work introduces an innovative architecture that combines the strengths of ChatGPT with a traditional information retrieval based chatbot framework to offer enhanced student support in higher education. Our empirical evaluations underscore the high promise of this approach.