@inproceedings{saha-etal-2025-nlip,
title = "{NLIP} at {BEA} 2025 Shared Task: Evaluation of Pedagogical Ability of {AI} Tutors",
author = "Saha, Trishita and
Ganguli, Shrenik and
Desarkar, Maunendra Sankar",
editor = {Kochmar, Ekaterina and
Alhafni, Bashar and
Bexte, Marie and
Burstein, Jill and
Horbach, Andrea and
Laarmann-Quante, Ronja and
Tack, Ana{\"i}s and
Yaneva, Victoria and
Yuan, Zheng},
booktitle = "Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.bea-1.99/",
pages = "1242--1253",
ISBN = "979-8-89176-270-1",
abstract = "This paper describes the system created for the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors. The task aims to assess how well AI tutors identify and locate errors made by students, provide guidance and ensure actionability, among other features of their responses in educational dialogues. Transformer-based models, especially DeBERTa and RoBERTa, are improved by multitask learning, threshold tweaking, ordinal regression, and oversampling. The efficiency of pedagogically driven training methods and bespoke transformer models for evaluating AI tutor quality is demonstrated by the high performance of their best systems across all evaluation tracks."
}
Markdown (Informal)
[NLIP at BEA 2025 Shared Task: Evaluation of Pedagogical Ability of AI Tutors](https://preview.aclanthology.org/acl25-workshop-ingestion/2025.bea-1.99/) (Saha et al., BEA 2025)
ACL