Ruffle&Riley: Insights from Designing and Evaluating a Large Language Model-Based Conversational Tutoring System

TL;DR

This paper presents Ruffle&Riley, a large language model-based conversational tutoring system that automates content creation and script orchestration, enhancing user engagement and understanding in biology lessons, with open-source availability for future research.

Contribution

The paper introduces a novel LLM-based CTS that automates content authoring and dialogue management, demonstrating its effectiveness through user studies and providing insights for future instructional design.

Findings

High user engagement and perceived helpfulness.

No significant short-term learning gains compared to reading.

System architecture offers valuable insights for future CTS design.

Abstract

Conversational tutoring systems (CTSs) offer learning experiences through interactions based on natural language. They are recognized for promoting cognitive engagement and improving learning outcomes, especially in reasoning tasks. Nonetheless, the cost associated with authoring CTS content is a major obstacle to widespread adoption and to research on effective instructional design. In this paper, we discuss and evaluate a novel type of CTS that leverages recent advances in large language models (LLMs) in two ways: First, the system enables AI-assisted content authoring by inducing an easily editable tutoring script automatically from a lesson text. Second, the system automates the script orchestration in a learning-by-teaching format via two LLM-based agents (Ruffle&Riley) acting as a student and a professor. The system allows for free-form conversations that follow the ITS-typical inner and outer loop structure. We evaluate Ruffle&Riley's ability to support biology lessons in two between-subject online user studies (N = 200) comparing the system to simpler QA chatbots and reading activity. Analyzing system usage patterns, pre/post-test scores and user experience surveys, we find that Ruffle&Riley users report high levels of engagement, understanding and perceive the offered support as helpful. Even though Ruffle&Riley users require more time to complete the activity, we did not find significant differences in short-term learning gains over the reading activity. Our system architecture and user study provide various insights for designers of future CTSs. We further open-source our system to support ongoing research on effective instructional design of LLM-based learning technologies.