QUD-Empowered LLM Essay Co-writing Tool

Developing an innovative essay co-writing tool that leverages the linguistic Questions Under Discussion (QUD) framework to generate pedagogically appropriate questions that scaffold student learning. The system uses a multi-agent architecture to extract questions from reading materials and student drafts, classifies them into obligatory and optional tiers, and integrates with Google Docs for seamless accessibility. Employs FAISS for similarity search, QAPyramid for evaluation, and includes planned human experimentation on Prolific to validate effectiveness against baseline and LLM-prompting conditions. Masters Capstone project with team members Neng Wan, Kiara LaRocca, and Ting-Yu Chou.