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

Shuzhou Yuan, Willliam LaCroix, Hardik Ghoshal, Ercong Nie, Michael Färber


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.
Anthology ID:
2026.lrec-1.837
Volume:
Proceedings of the Fifteenth Language Resources and Evaluation Conference
Month:
May
Year:
2026
Address:
Palma de Mallorca, Spain
Editors:
Stelios Piperidis, Núria Bel, Henk van den Heuvel, Nancy Ide, Simon Krek, Antonio Toral
Venue:
LREC
SIG:
Publisher:
ELRA Language Resource Association
Note:
Pages:
10677–10687
Language:
External URL:
https://lrec.elra.info/lrec2026-main-837
DOI:
10.63317/447hbzyohzyf
Bibkey:
Cite (ACL):
Shuzhou Yuan, Willliam LaCroix, Hardik Ghoshal, Ercong Nie, and Michael Färber. 2026. CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation. In Proceedings of the Fifteenth Language Resources and Evaluation Conference, pages 10677–10687, Palma de Mallorca, Spain. ELRA Language Resource Association.
Cite (Informal):
CoDAE: Adapting Large Language Models for Education via Chain-of-Thought Data Augmentation (Yuan et al., LREC 2026)
Copy Citation: