SPL: A Socratic Playground for Learning Powered by Large Language Model

SPL (Socratic Playground for Learning) is a GPT-4-powered dialogue-based intelligent tutoring system that implements the Socratic teaching method to foster critical thinking and self-reflection through interactive questioning and personalized adaptive dialogues. The paper presents pilot experimental results from essay writing tasks demonstrating the system's potential to improve tutoring interactions in K-12 educational contexts.

Dialogue-based Intelligent Tutoring Systems (ITSs) have significantly advanced adaptive and personalized learning by automating sophisticated human tutoring strategies within interactive dialogues. However, replicating the nuanced patterns of expert human communication remains a challenge in Natural Language Processing (NLP). Recent advancements in NLP, particularly Large Language Models (LLMs) such as OpenAI's GPT-4, offer promising solutions by providing human-like and context-aware responses

Source

Framework Categories

Tool Types

Tags