SocratiQ: A Generative AI-Powered Learning Companion for Personalized Education and Broader Accessibility

TL;DR

SocratiQ addresses the challenge of scalable personalized education by applying the Socratic method through generative AI within an interactive learning companion. It operationalizes Generative Learning via personalized explanations, adaptive assessments, and engaging dialogue, integrated into the CS249r ML Systems textbook with a token budget of $l=\!5000$ for quiz generation. The paper details a client-side, privacy-preserving implementation, a serverless LM pipeline, and optimization strategies (token budgeting, vectorization, and question caching), plus Bloom-based evaluation and a small student sprint study. Findings show that SocratiQ can deliver real-time explanations, adaptive quizzes, and gamified engagement while maintaining data privacy through a local-first architecture and cost-effective multi-service LM deployments, offering a practical blueprint for AI-enabled education in STEM fields.

Abstract

Traditional educational approaches often struggle to provide personalized and interactive learning experiences on a scale. In this paper, we present SocratiQ, an AI-powered educational assistant that addresses this challenge by implementing the Socratic method through adaptive learning technologies. The system employs a novel Generative AI-based learning framework that dynamically creates personalized learning pathways based on student responses and comprehension patterns. We provide an account of our integration methodology, system architecture, and evaluation framework, along with the technical and pedagogical challenges encountered during implementation and our solutions. Although our implementation focuses on machine learning systems education, the integration approaches we present can inform similar efforts across STEM fields. Through this work, our goal is to advance the understanding of how generative AI technologies can be designed and systematically incorporated into educational resources.

Figures (7)

• Figure 1: Students can dynamically adjust the academic level to match their learning preferences.
• Figure 2: As students progress through the textbook, a knowledge graph is built, tracking their reading progress and quiz performance for each section.
• Figure 3: Dashboard showcasing gamification elements, including badges for quiz streaks and progress bars, to enhance engagement and provide learning insights.
• Figure 4: Overview of achievement badges students can earn through quizzes.
• Figure 5: Socratiq displays a visualization of the frequencies of one's engagement with the app, inspired by the Github Contribution heatmap.