@inproceedings{dadwal-etal-2025-thapar,
title = "Thapar Titan/s : Fine-Tuning Pretrained Language Models with Contextual Augmentation for Mistake Identification in Tutor{--}Student Dialogues",
author = "Dadwal, Harsh and
Rastogi, Sparsh and
Bedi, Jatin",
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://aclanthology.org/2025.bea-1.103/",
doi = "10.18653/v1/2025.bea-1.103",
pages = "1278--1282",
ISBN = "979-8-89176-270-1",
abstract = "This paper presents Thapar Titan/s' submission to the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors. The shared task consists of five subtasks; our team ranked 18th in Mistake Identification, 15th in Mistake Location, and 18th in Actionability. However, in this paper, we focus exclusively on presenting results for Task 1: Mistake Identification, which evaluates a system{'}s ability to detect student mistakes.Our approach employs contextual data augmentation using a RoBERTa based masked language model to mitigate class imbalance, supplemented by oversampling and weighted loss training. Subsequently, we fine-tune three separate classifiers: RoBERTa, BERT, and DeBERTa for three-way classification aligned with task-specific annotation schemas. This modular and scalable pipeline enables a comprehensive evaluation of tutor feedback quality in educational dialogues."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dadwal-etal-2025-thapar">
<titleInfo>
<title>Thapar Titan/s : Fine-Tuning Pretrained Language Models with Contextual Augmentation for Mistake Identification in Tutor–Student Dialogues</title>
</titleInfo>
<name type="personal">
<namePart type="given">Harsh</namePart>
<namePart type="family">Dadwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sparsh</namePart>
<namePart type="family">Rastogi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jatin</namePart>
<namePart type="family">Bedi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Kochmar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bashar</namePart>
<namePart type="family">Alhafni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie</namePart>
<namePart type="family">Bexte</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jill</namePart>
<namePart type="family">Burstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrea</namePart>
<namePart type="family">Horbach</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronja</namePart>
<namePart type="family">Laarmann-Quante</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anaïs</namePart>
<namePart type="family">Tack</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Victoria</namePart>
<namePart type="family">Yaneva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zheng</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-270-1</identifier>
</relatedItem>
<abstract>This paper presents Thapar Titan/s’ submission to the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors. The shared task consists of five subtasks; our team ranked 18th in Mistake Identification, 15th in Mistake Location, and 18th in Actionability. However, in this paper, we focus exclusively on presenting results for Task 1: Mistake Identification, which evaluates a system’s ability to detect student mistakes.Our approach employs contextual data augmentation using a RoBERTa based masked language model to mitigate class imbalance, supplemented by oversampling and weighted loss training. Subsequently, we fine-tune three separate classifiers: RoBERTa, BERT, and DeBERTa for three-way classification aligned with task-specific annotation schemas. This modular and scalable pipeline enables a comprehensive evaluation of tutor feedback quality in educational dialogues.</abstract>
<identifier type="citekey">dadwal-etal-2025-thapar</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.103</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.103/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1278</start>
<end>1282</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thapar Titan/s : Fine-Tuning Pretrained Language Models with Contextual Augmentation for Mistake Identification in Tutor–Student Dialogues
%A Dadwal, Harsh
%A Rastogi, Sparsh
%A Bedi, Jatin
%Y Kochmar, Ekaterina
%Y Alhafni, Bashar
%Y Bexte, Marie
%Y Burstein, Jill
%Y Horbach, Andrea
%Y Laarmann-Quante, Ronja
%Y Tack, Anaïs
%Y Yaneva, Victoria
%Y Yuan, Zheng
%S Proceedings of the 20th Workshop on Innovative Use of NLP for Building Educational Applications (BEA 2025)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-270-1
%F dadwal-etal-2025-thapar
%X This paper presents Thapar Titan/s’ submission to the BEA 2025 Shared Task on Pedagogical Ability Assessment of AI-powered Tutors. The shared task consists of five subtasks; our team ranked 18th in Mistake Identification, 15th in Mistake Location, and 18th in Actionability. However, in this paper, we focus exclusively on presenting results for Task 1: Mistake Identification, which evaluates a system’s ability to detect student mistakes.Our approach employs contextual data augmentation using a RoBERTa based masked language model to mitigate class imbalance, supplemented by oversampling and weighted loss training. Subsequently, we fine-tune three separate classifiers: RoBERTa, BERT, and DeBERTa for three-way classification aligned with task-specific annotation schemas. This modular and scalable pipeline enables a comprehensive evaluation of tutor feedback quality in educational dialogues.
%R 10.18653/v1/2025.bea-1.103
%U https://aclanthology.org/2025.bea-1.103/
%U https://doi.org/10.18653/v1/2025.bea-1.103
%P 1278-1282
Markdown (Informal)
[Thapar Titan/s : Fine-Tuning Pretrained Language Models with Contextual Augmentation for Mistake Identification in Tutor–Student Dialogues](https://aclanthology.org/2025.bea-1.103/) (Dadwal et al., BEA 2025)
ACL