Opportunities and Challenges in Neural Dialog Tutoring

TL;DR

This paper evaluates neural language models for dialog tutoring, revealing their strengths in constrained scenarios and highlighting significant challenges like reasoning errors and engagement issues in real educational settings.

Contribution

It provides a comprehensive analysis of current neural dialog tutors, identifying key limitations and outlining future research directions for effective educational applications.

Findings

Models perform well in constrained scenarios with few concepts.

Models and annotations show low fairness and engagement.

45% of conversations contain reasoning errors.

Abstract

Designing dialog tutors has been challenging as it involves modeling the diverse and complex pedagogical strategies employed by human tutors. Although there have been significant recent advances in neural conversational systems using large language models (LLMs) and growth in available dialog corpora, dialog tutoring has largely remained unaffected by these advances. In this paper, we rigorously analyze various generative language models on two dialog tutoring datasets for language learning using automatic and human evaluations to understand the new opportunities brought by these advances as well as the challenges we must overcome to build models that would be usable in real educational settings. We find that although current approaches can model tutoring in constrained learning scenarios when the number of concepts to be taught and possible teacher strategies are small, they perform poorly in less constrained scenarios. Our human quality evaluation shows that both models and ground-truth annotations exhibit low performance in terms of equitable tutoring, which measures learning opportunities for students and how engaging the dialog is. To understand the behavior of our models in a real tutoring setting, we conduct a user study using expert annotators and find a significantly large number of model reasoning errors in 45% of conversations. Finally, we connect our findings to outline future work.