ChatEd: A Chatbot Leveraging ChatGPT for an Enhanced Learning Experience in Higher Education

TL;DR

This work tackles the challenge of deploying large language models in higher education without sacrificing accuracy or verifiability. It introduces ChatEd, a retrieval-augmented chatbot that uses a Per-course Context-Specific Database in conjunction with a large language model (ChatGPT 3.5 turbo) to deliver contextually grounded, source-backed responses. By indexing instructor-provided materials and querying them before prompting the LLM, ChatEd achieves higher relevance, accuracy, and helpfulness for course-specific questions while avoiding local model training. The approach demonstrates strong potential for scalable, instructor-friendly deployment that enhances learning experiences through contextual dialogue and verifiable references, with promising results and clear avenues for expansion.

Abstract

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.

Figures (5)

• Figure 1: Chatbot User Interface and Example Conversation
• Figure 2: Instructor Interface
• Figure 3: ChatEd Chatbot Architecture
• Figure 4: Example Interaction for Q&A Test
• Figure 5: Example of Switching Contexts in a Conversation