Public repository of the MathBuddy project.
For installation instructions see:
Link to the showcase video: https://youtu.be/ZUjgmOw9GM0
✨ If you find our work helpful, please consider citing with:
Arxiv version (till proceedings are released):
@article{kar2025mathbuddy,
title={MathBuddy: A Multimodal System for Affective Math Tutoring},
author={Kar, Debanjana and B{\"o}ss, Leopold and Braca, Dacia and Dennerlein, Sebastian Maximilian and Hubig, Nina Christine and Wintersberger, Philipp and Hou, Yufang},
journal={arXiv preprint arXiv:2508.19993},
year={2025}
}
Proceedings placeholder:
@inproceedings{kar-etal-2025-mathbuddy,
title = "MathBuddy: A Multimodal System for Affective Math Tutoring",
author = "Kar, Debanjana and
B{\"o}ss, Leopold and
Braca, Dacia and
Dennerlein, Sebastian Maximilian and
Hubig, Nina Christine and
Wintersberger, Philipp and
Hou, Yufang",
editor = "",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
month = nov,
year = "2025",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = ""https://aclanthology.org/2025.emnlp-demo.1/",",
doi = "",
pages = "",
abstract = "The rapid adoption of LLM-based conversational systems is already transforming the landscape of educational technology. However, the current state-of-the-art learning models do not take into account the student’s affective states. Multiple studies in educational psychology support the claim that positive or negative emotional states can impact a student’s learning capabilities. To bridge this gap, we present MathBuddy, an emotionally aware LLM-powered Math Tutor, which dynamically models the student’s emotions and maps them to relevant pedagogical strategies, making the tutor-student conversation a more empathetic one. The student’s emotions are captured from the conversational text as well as from their facial expressions. The student’s emotions are aggregated from both modalities to confidently prompt our LLM Tutor for an emotionally-aware response. We have effectively evaluated our model using automatic evaluation metrics across eight pedagogical dimensions and user studies. We report a massive 23 point performance gain using the win rate and a 3 point gain at an overall level using DAMR scores which strongly supports our hypothesis of improving LLM-based tutor’s pedagogical abilities by modeling students’ emotions. Our dataset and code is open sourced here: https://github.com/ITU-NLP/MathBuddy."
}