CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation

Abstract

Large Language Models (LLMs) are increasingly employed as AI tutors in education due to their scalability and potential for personalized instruction. However, off-the-shelf LLMs often underperform in educational settings, exhibiting limitations such as providing answers too readily, failing to adapt their responses to students’ uncertainty, and remaining susceptible to emotionally manipulative prompts. To address these challenges, we introduce CoDAE, a framework that adapts LLMs for educational use through Chain-of-Thought (CoT) data augmentation. We collect real-world dialogues between students and a ChatGPT-based tutor and enrich them using CoT prompting to promote step-by-step reasoning and pedagogically aligned guidance. Furthermore, we design targeted dialogue cases to explicitly mitigate three key limitations: over-compliance, low response adaptivity, and threat vulnerability. We fine-tune four open-source LLMs on different variants of the augmented datasets and evaluate them in simulated educational scenarios using both automatic metrics and LLM-as-a-judge assessments. Our results show that models fine-tuned with CoDAE deliver more pedagogically appropriate guidance, promote student reflection and more effectively prevent premature answer disclosure.

Resources

Details