@inproceedings{fan-etal-2025-bjtu,
title = "{BJTU} at {BEA} 2025 Shared Task: Task-Aware Prompt Tuning and Data Augmentation for Evaluating {AI} Math Tutors",
author = "Fan, Yuming and
Tan, Chuangchuang and
Song, Wenyu",
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-1.82/",
doi = "10.18653/v1/2025.bea-1.82",
pages = "1073--1077",
ISBN = "979-8-89176-270-1",
abstract = "We present a prompt-based evaluation framework for assessing AI-generated math tutoring responses across four pedagogical dimensions: mistake identification, mistake location, guidance quality, and actionability. Our approach leverages task-aware prompt tuning on a large language model, supplemented by data augmentation techniques including dialogue shuffling and class-balanced downsampling. In experiments on the BEA 2025 Shared Task benchmark, our system achieved first place in mistake identification and strong top-five rankings in the other tracks. These results demonstrate the effectiveness of structured prompting and targeted augmentation for enhancing LLMs' ability to provide pedagogically meaningful feedback."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fan-etal-2025-bjtu">
<titleInfo>
<title>BJTU at BEA 2025 Shared Task: Task-Aware Prompt Tuning and Data Augmentation for Evaluating AI Math Tutors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuming</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chuangchuang</namePart>
<namePart type="family">Tan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenyu</namePart>
<namePart type="family">Song</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>We present a prompt-based evaluation framework for assessing AI-generated math tutoring responses across four pedagogical dimensions: mistake identification, mistake location, guidance quality, and actionability. Our approach leverages task-aware prompt tuning on a large language model, supplemented by data augmentation techniques including dialogue shuffling and class-balanced downsampling. In experiments on the BEA 2025 Shared Task benchmark, our system achieved first place in mistake identification and strong top-five rankings in the other tracks. These results demonstrate the effectiveness of structured prompting and targeted augmentation for enhancing LLMs’ ability to provide pedagogically meaningful feedback.</abstract>
<identifier type="citekey">fan-etal-2025-bjtu</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.82</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.82/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1073</start>
<end>1077</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BJTU at BEA 2025 Shared Task: Task-Aware Prompt Tuning and Data Augmentation for Evaluating AI Math Tutors
%A Fan, Yuming
%A Tan, Chuangchuang
%A Song, Wenyu
%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 fan-etal-2025-bjtu
%X We present a prompt-based evaluation framework for assessing AI-generated math tutoring responses across four pedagogical dimensions: mistake identification, mistake location, guidance quality, and actionability. Our approach leverages task-aware prompt tuning on a large language model, supplemented by data augmentation techniques including dialogue shuffling and class-balanced downsampling. In experiments on the BEA 2025 Shared Task benchmark, our system achieved first place in mistake identification and strong top-five rankings in the other tracks. These results demonstrate the effectiveness of structured prompting and targeted augmentation for enhancing LLMs’ ability to provide pedagogically meaningful feedback.
%R 10.18653/v1/2025.bea-1.82
%U https://aclanthology.org/2025.bea-1.82/
%U https://doi.org/10.18653/v1/2025.bea-1.82
%P 1073-1077
Markdown (Informal)
[BJTU at BEA 2025 Shared Task: Task-Aware Prompt Tuning and Data Augmentation for Evaluating AI Math Tutors](https://aclanthology.org/2025.bea-1.82/) (Fan et al., BEA 2025)
ACL