ConvoLearn: A Dataset of Constructivist Tutor-Student Dialogue
This work addresses the need for more effective AI tutors in education by providing a dataset and framework for constructivist learning, though it is incremental as it builds on existing fine-tuning methods.
The paper tackles the problem of LLMs' pedagogical limitations in education by introducing ConvoLearn, a dataset of tutor-student dialogues, and shows that fine-tuning Mistral 7B on it significantly improves performance in knowledge-building strategies, with human evaluation scores increasing from M=2.59 to M=4.10.
In educational applications, LLMs exhibit several fundamental pedagogical limitations, such as their tendency to reveal solutions rather than support dialogic learning. We introduce ConvoLearn (https://huggingface.co/datasets/masharma/convolearn ), a dataset grounded in knowledge building theory that operationalizes six core pedagogical dimensions: cognitive engagement, formative assessment, accountability, cultural responsiveness, metacognition, and power dynamics. We construct a semi-synthetic dataset of 1250 tutor-student dialogues (20 turns each) in middle school Earth Science through controlled interactions between human teachers and a simulated student. Using QLoRA, we demonstrate that training on this dataset meaningfully shifts LLM behavior toward knowledge-building strategies. Human evaluation by 31 teachers shows our fine-tuned Mistral 7B (M = 4.10, SD = 1.03) significantly outperforms both its base version (M = 2.59, SD = 1.11) and Claude Sonnet 4.5 (M = 2.87, SD = 1.29) overall. This work establishes a potential framework to guide future development and evaluation of constructivist AI tutors.