BD at BEA 2025 Shared Task: MPNet Ensembles for Pedagogical Mistake Identification and Localization in AI Tutor Responses

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Rohan, Shadman, Apan, Ishita Sur, Shochcho, Muhtasim Ibteda, Fahim, Md, Rahman, Mohammad Ashfaq Ur, Rahman, AKM Mahbubur, Ali, Amin Ahsan
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918042993164288
author Rohan, Shadman
Apan, Ishita Sur
Shochcho, Muhtasim Ibteda
Fahim, Md
Rahman, Mohammad Ashfaq Ur
Rahman, AKM Mahbubur
Ali, Amin Ahsan
author_facet Rohan, Shadman
Apan, Ishita Sur
Shochcho, Muhtasim Ibteda
Fahim, Md
Rahman, Mohammad Ashfaq Ur
Rahman, AKM Mahbubur
Ali, Amin Ahsan
contents We present Team BD's submission to the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors, under Track 1 (Mistake Identification) and Track 2 (Mistake Location). Both tracks involve three-class classification of tutor responses in educational dialogues - determining if a tutor correctly recognizes a student's mistake (Track 1) and whether the tutor pinpoints the mistake's location (Track 2). Our system is built on MPNet, a Transformer-based language model that combines BERT and XLNet's pre-training advantages. We fine-tuned MPNet on the task data using a class-weighted cross-entropy loss to handle class imbalance, and leveraged grouped cross-validation (10 folds) to maximize the use of limited data while avoiding dialogue overlap between training and validation. We then performed a hard-voting ensemble of the best models from each fold, which improves robustness and generalization by combining multiple classifiers. Our approach achieved strong results on both tracks, with exact-match macro-F1 scores of approximately 0.7110 for Mistake Identification and 0.5543 for Mistake Location on the official test set. We include comprehensive analysis of our system's performance, including confusion matrices and t-SNE visualizations to interpret classifier behavior, as well as a taxonomy of common errors with examples. We hope our ensemble-based approach and findings provide useful insights for designing reliable tutor response evaluation systems in educational dialogue settings.
format Preprint
id arxiv_https___arxiv_org_abs_2506_01817
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle BD at BEA 2025 Shared Task: MPNet Ensembles for Pedagogical Mistake Identification and Localization in AI Tutor Responses
Rohan, Shadman
Apan, Ishita Sur
Shochcho, Muhtasim Ibteda
Fahim, Md
Rahman, Mohammad Ashfaq Ur
Rahman, AKM Mahbubur
Ali, Amin Ahsan
Computation and Language
We present Team BD's submission to the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors, under Track 1 (Mistake Identification) and Track 2 (Mistake Location). Both tracks involve three-class classification of tutor responses in educational dialogues - determining if a tutor correctly recognizes a student's mistake (Track 1) and whether the tutor pinpoints the mistake's location (Track 2). Our system is built on MPNet, a Transformer-based language model that combines BERT and XLNet's pre-training advantages. We fine-tuned MPNet on the task data using a class-weighted cross-entropy loss to handle class imbalance, and leveraged grouped cross-validation (10 folds) to maximize the use of limited data while avoiding dialogue overlap between training and validation. We then performed a hard-voting ensemble of the best models from each fold, which improves robustness and generalization by combining multiple classifiers. Our approach achieved strong results on both tracks, with exact-match macro-F1 scores of approximately 0.7110 for Mistake Identification and 0.5543 for Mistake Location on the official test set. We include comprehensive analysis of our system's performance, including confusion matrices and t-SNE visualizations to interpret classifier behavior, as well as a taxonomy of common errors with examples. We hope our ensemble-based approach and findings provide useful insights for designing reliable tutor response evaluation systems in educational dialogue settings.
title BD at BEA 2025 Shared Task: MPNet Ensembles for Pedagogical Mistake Identification and Localization in AI Tutor Responses
topic Computation and Language
url https://arxiv.org/abs/2506.01817