CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation
This addresses the need for more effective and resilient AI tutors in educational settings, though it is incremental as it builds on existing fine-tuning and data augmentation methods.
The paper tackled the problem of large language models underperforming as AI tutors by introducing CoDAE, a framework using chain-of-thought data augmentation to adapt them for education, resulting in models that provide more pedagogically appropriate guidance and better support reasoning processes.
Large Language Models (LLMs) are increasingly employed as AI tutors due to their scalability and potential for personalized instruction. However, off-the-shelf LLMs often underperform in educational settings: they frequently reveal answers too readily, fail to adapt their responses to student uncertainty, and remain vulnerable 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, better support reasoning processes, and effectively resist premature answer disclosure.