The Textbook of Tomorrow: Rethinking Course Material Interfacing in the Era of GPT
Audrey Olson, Pratyusha Maiti, Ashok Goel
TL;DR
Online LMS course readings often exist as static digital twins, limiting student engagement and equity in processing text. The paper presents a PDF-embedded intelligent textbook interface that uses a retrieval-augmented generation (RAG) based virtual teaching assistant built on React and GPT-4o to chat with readings, provide summaries and explanations, and generate quiz questions. Key contributions include seamless front-end integration of reading content with AI-driven Q&A, in-text reference highlighting for grounded answers, and a Leitner-system-inspired path toward personalized quizzes, supported by initial usability studies and a roadmap for latency reduction and personalization. The approach aims to scale within LMS environments to enhance cognitive presence and sustained discourse in online learning, with ongoing evaluation across semesters and courses.
Abstract
Online Learning Management Systems (LMSs), such as Blackboard and Canvas, have existed for decades. Yet, course readings, when provided at all, consistently exist as simple digital twins to their real-life counterparts. While online tools and resources exist to help students process digital texts more efficiently or in ways better suited to their learning styles, knowledge about such resources is not evenly distributed and creates a gulf in advantage between students. This paper proposes the courseware integration of "smart" textbooks, a newfound way for students to chat with their readings, receive summaries and explanations for highlighted text, and generate quiz questions via an AI agent embedded in their online course material. Future iterations of the software aim to add in-context reference highlighting for AI-generated answers and personalized tunings for the end learner.