LittleMu: Deploying an Online Virtual Teaching Assistant via Heterogeneous Sources Integration and Chain of Teach Prompts

TL;DR

LittleMu is a virtual MOOC teaching assistant that integrates heterogeneous knowledge sources and uses chain-of-teach prompts to provide question answering and chit-chat services with minimal training data, serving over 80,000 users.

Contribution

This work introduces LittleMu, a virtual teaching assistant that combines knowledge integration and innovative prompting techniques to support online education with limited labeled data.

Findings

Supported over 80,000 users and 300,000 queries since 2020

Effectively integrates multiple knowledge sources for accurate answers

Utilizes chain-of-teach prompts to handle complex questions

Abstract

Teaching assistants have played essential roles in the long history of education. However, few MOOC platforms are providing human or virtual teaching assistants to support learning for massive online students due to the complexity of real-world online education scenarios and the lack of training data. In this paper, we present a virtual MOOC teaching assistant, LittleMu with minimum labeled training data, to provide question answering and chit-chat services. Consisting of two interactive modules of heterogeneous retrieval and language model prompting, LittleMu first integrates structural, semi- and unstructured knowledge sources to support accurate answers for a wide range of questions. Then, we design delicate demonstrations named "Chain of Teach" prompts to exploit the large-scale pre-trained model to handle complex uncollected questions. Except for question answering, we develop other educational services such as knowledge-grounded chit-chat. We test the system's performance via both offline evaluation and online deployment. Since May 2020, our LittleMu system has served over 80,000 users with over 300,000 queries from over 500 courses on XuetangX MOOC platform, which continuously contributes to a more convenient and fair education. Our code, services, and dataset will be available at https://github.com/THU-KEG/VTA.