Educational Personalized Learning Path Planning with Large Language Models

TL;DR

The paper addresses the need for scalable, adaptive, and transparent educational PLPP by integrating large language models with carefully crafted prompts. It presents a prompt-based PLPP pipeline featuring Initial Assessment, Clarification, and Explanatory prompts, coupled with multi-turn dialogues to tailor learning paths to individual learners. Experimental results using LLama-2-70B and GPT-4 show significant improvements in accuracy, user satisfaction, and path quality, with GPT-4 yielding the largest gains, and a long-term validation indicating better test performance and retention. The work demonstrates the potential of explainable, interactive, and personalized education powered by prompt-engineered LLMs, offering a practical pathway toward more effective learning experiences.

Abstract

Educational Personalized Learning Path Planning (PLPP) aims to tailor learning experiences to individual learners' needs, enhancing learning efficiency and engagement. Despite its potential, traditional PLPP systems often lack adaptability, interactivity, and transparency. This paper proposes a novel approach integrating Large Language Models (LLMs) with prompt engineering to address these challenges. By designing prompts that incorporate learner-specific information, our method guides LLMs like LLama-2-70B and GPT-4 to generate personalized, coherent, and pedagogically sound learning paths. We conducted experiments comparing our method with a baseline approach across various metrics, including accuracy, user satisfaction, and the quality of learning paths. The results show significant improvements in all areas, particularly with GPT-4, demonstrating the effectiveness of prompt engineering in enhancing PLPP. Additional long-term impact analysis further validates our method's potential to improve learner performance and retention. This research highlights the promise of LLMs and prompt engineering in advancing personalized education.