Strategize Before Teaching: A Conversational Tutoring System with Pedagogy Self-Distillation
This work addresses the problem of enhancing educational AI systems for students by improving conversational tutoring, though it is incremental as it builds on existing methods for strategy integration.
The paper tackles the challenge of making conversational tutoring systems more engaging and pedagogically diverse by jointly predicting teaching strategies and generating tutor responses, rather than using predefined strategies. The proposed framework, which includes a self-distillation mechanism, was benchmarked on three datasets, showing how teaching strategies impact dialog tutoring.
Conversational tutoring systems (CTSs) aim to help students master educational material with natural language interaction in the form of a dialog. CTSs have become a key pillar in educational data mining research. A key challenge in CTSs is to engage the student in the conversation while exposing them to a diverse set of teaching strategies, akin to a human teacher, thereby, helping them learn in the process. Different from previous work that generates responses given the strategies as input, we propose to jointly predict teaching strategies and generate tutor responses accordingly, which fits a more realistic application scenario. We benchmark several competitive models on three dialog tutoring datasets and propose a unified framework that combines teaching response generation and pedagogical strategy prediction, where a self-distillation mechanism is adopted to guide the teaching strategy learning and facilitate tutor response generation. Our experiments and analyses shed light on how teaching strategies affect dialog tutoring.