YA-TA: Towards Personalized Question-Answering Teaching Assistants using Instructor-Student Dual Retrieval-augmented Knowledge Fusion

TL;DR

This paper introduces YA-TA, a personalized virtual teaching assistant that uses a dual retrieval and knowledge fusion framework to provide tailored, lecture-grounded responses, improving student engagement and support in large classes.

Contribution

The paper presents the DRAKE framework for dual knowledge retrieval and fusion, enabling YA-TA to generate personalized responses grounded in instructor and student knowledge.

Findings

DRAKE outperforms baseline models in response relevance and accuracy.

YA-TA effectively personalizes responses in real classroom settings.

Extensions like Q&A boards enhance student learning experience.

Abstract

Engagement between instructors and students plays a crucial role in enhancing students'academic performance. However, instructors often struggle to provide timely and personalized support in large classes. To address this challenge, we propose a novel Virtual Teaching Assistant (VTA) named YA-TA, designed to offer responses to students that are grounded in lectures and are easy to understand. To facilitate YA-TA, we introduce the Dual Retrieval-augmented Knowledge Fusion (DRAKE) framework, which incorporates dual retrieval of instructor and student knowledge and knowledge fusion for tailored response generation. Experiments conducted in real-world classroom settings demonstrate that the DRAKE framework excels in aligning responses with knowledge retrieved from both instructor and student sides. Furthermore, we offer additional extensions of YA-TA, such as a Q&A board and self-practice tools to enhance the overall learning experience. Our video is publicly available.