@inproceedings{bhattacharyya-etal-2025-lexilogic-bea,
title = "{L}exi{L}ogic at {BEA} 2025 Shared Task: Fine-tuning Transformer Language Models for the Pedagogical Skill Evaluation of {LLM}-based tutors",
author = "Bhattacharyya, Souvik and
Roy, Billodal and
M, Niranjan and
Gupta, Pranav",
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-1.93/",
doi = "10.18653/v1/2025.bea-1.93",
pages = "1180--1186",
ISBN = "979-8-89176-270-1",
abstract = "While large language models show promise as AI tutors, evaluating their pedagogical capabilities remains challenging. In this paper, we, team LexiLogic presents our participation in the BEA 2025 shared task on evaluating AI tutors across five dimensions: Mistake Identification, Mistake Location, Providing Guidance, Actionability, and Tutor Identification. We approach all tracks as classification tasks using fine-tuned transformer models on a dataset of 300 educational dialogues between a student and a tutor in the mathematical domain. Our results show varying performance across tracks, with macro average F1 scores ranging from 0.47 to 0.82, achieving rankings between 4th and 31st place. Such models have the potential to be used in developing automated scoring metrics for assessing the pedagogical skills of AI math tutors."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhattacharyya-etal-2025-lexilogic-bea">
<titleInfo>
<title>LexiLogic at BEA 2025 Shared Task: Fine-tuning Transformer Language Models for the Pedagogical Skill Evaluation of LLM-based tutors</title>
</titleInfo>
<name type="personal">
<namePart type="given">Souvik</namePart>
<namePart type="family">Bhattacharyya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Billodal</namePart>
<namePart type="family">Roy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niranjan</namePart>
<namePart type="family">M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pranav</namePart>
<namePart type="family">Gupta</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>While large language models show promise as AI tutors, evaluating their pedagogical capabilities remains challenging. In this paper, we, team LexiLogic presents our participation in the BEA 2025 shared task on evaluating AI tutors across five dimensions: Mistake Identification, Mistake Location, Providing Guidance, Actionability, and Tutor Identification. We approach all tracks as classification tasks using fine-tuned transformer models on a dataset of 300 educational dialogues between a student and a tutor in the mathematical domain. Our results show varying performance across tracks, with macro average F1 scores ranging from 0.47 to 0.82, achieving rankings between 4th and 31st place. Such models have the potential to be used in developing automated scoring metrics for assessing the pedagogical skills of AI math tutors.</abstract>
<identifier type="citekey">bhattacharyya-etal-2025-lexilogic-bea</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.93</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.93/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1180</start>
<end>1186</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LexiLogic at BEA 2025 Shared Task: Fine-tuning Transformer Language Models for the Pedagogical Skill Evaluation of LLM-based tutors
%A Bhattacharyya, Souvik
%A Roy, Billodal
%A M, Niranjan
%A Gupta, Pranav
%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 bhattacharyya-etal-2025-lexilogic-bea
%X While large language models show promise as AI tutors, evaluating their pedagogical capabilities remains challenging. In this paper, we, team LexiLogic presents our participation in the BEA 2025 shared task on evaluating AI tutors across five dimensions: Mistake Identification, Mistake Location, Providing Guidance, Actionability, and Tutor Identification. We approach all tracks as classification tasks using fine-tuned transformer models on a dataset of 300 educational dialogues between a student and a tutor in the mathematical domain. Our results show varying performance across tracks, with macro average F1 scores ranging from 0.47 to 0.82, achieving rankings between 4th and 31st place. Such models have the potential to be used in developing automated scoring metrics for assessing the pedagogical skills of AI math tutors.
%R 10.18653/v1/2025.bea-1.93
%U https://aclanthology.org/2025.bea-1.93/
%U https://doi.org/10.18653/v1/2025.bea-1.93
%P 1180-1186
Markdown (Informal)
[LexiLogic at BEA 2025 Shared Task: Fine-tuning Transformer Language Models for the Pedagogical Skill Evaluation of LLM-based tutors](https://aclanthology.org/2025.bea-1.93/) (Bhattacharyya et al., BEA 2025)
ACL