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

2025-02-01

AI Summary

Traditional education struggles to deliver personalized, highly interactive instruction at scale. To address this, we propose a Socratic-dialogue-inspired learning companion framework that integrates large language models (LLMs), response-driven dynamic graph reasoning, student cognitive state modeling, and an educational knowledge graph. This architecture enables real-time analysis of learning behaviors and generates interpretable, pedagogy-guided, adaptive learning pathways. Our key contribution is the first principled integration of Socratic pedagogy into the core architecture of generative AI—grounded in educational theory yet engineered for practical deployment. In a controlled empirical study within a machine learning course, the framework significantly increased student engagement (+37%) and mastery of core concepts (+29%). These results demonstrate its transferability across STEM domains and its viability for scalable, personalized learning systems.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Search and Optimization: Learning to Search
• Natural Language Processing: (Large) Language Models

Application Category

• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

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.

Problem

• Traditional Education
• Personalized Learning
• Interactive Experience

Innovation

• Socratic questioning
• personalized learning
• AI educational assistant