Jill Watson: A Virtual Teaching Assistant powered by ChatGPT

TL;DR

This paper presents Jill Watson, a modular, ChatGPT-powered virtual teaching assistant that requires no prior training, integrates new APIs easily, and outperforms previous systems while ensuring safety and versatility in educational settings.

Contribution

Introduces Jill Watson, a novel ChatGPT-based VTA with a modular design, API integration, and safety features, enhancing educational AI applications without extensive training data.

Findings

Outperforms legacy Jill Watson and OpenAI Assistants

Uses publicly available resources for reproducibility

Reduces hallucinations and toxicity through safety measures

Abstract

Conversational AI agents often require extensive datasets for training that are not publicly released, are limited to social chit-chat or handling a specific domain, and may not be easily extended to accommodate the latest advances in AI technologies. This paper introduces Jill Watson, a conversational Virtual Teaching Assistant (VTA) leveraging the capabilities of ChatGPT. Jill Watson based on ChatGPT requires no prior training and uses a modular design to allow the integration of new APIs using a skill-based architecture inspired by XiaoIce. Jill Watson is also well-suited for intelligent textbooks as it can process and converse using multiple large documents. We exclusively utilize publicly available resources for reproducibility and extensibility. Comparative analysis shows that our system outperforms the legacy knowledge-based Jill Watson as well as the OpenAI Assistants service. We employ many safety measures that reduce instances of hallucinations and toxicity. The paper also includes real-world examples from a classroom setting that demonstrate different features of Jill Watson and its effectiveness.