@inproceedings{gongora-etal-2025-retuyt,
title = "{RETUYT}-{INCO} at {BEA} 2025 Shared Task: How Far Can Lightweight Models Go in {AI}-powered Tutor Evaluation?",
author = "G{\'o}ngora, Santiago and
Sastre, Ignacio and
Robaina, Santiago and
Remersaro, Ignacio and
Chiruzzo, Luis and
Ros{\'a}, Aiala",
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-1.89/",
doi = "10.18653/v1/2025.bea-1.89",
pages = "1135--1144",
ISBN = "979-8-89176-270-1",
abstract = "In this paper, we present the RETUYT-INCO participation at the BEA 2025 shared task. Our participation was characterized by the decision of using relatively small models, with fewer than 1B parameters. This self-imposed restriction tries to represent the conditions in which many research groups or institutions are in the Global South, where computational power is not easily accessible due to its prohibitive cost. Even under this restrictive self-imposed setting, our models managed to stay competitive with the rest of teams that participated in the shared task. According to the exact F1 scores published by the organizers, our models had the following distances with respect to the winners: 6.46 in Track 1; 10.24 in Track 2; 7.85 in Track 3; 9.56 in Track 4; and 13.13 in Track 5. Considering that the minimum difference with a winner team is 6.46 points {---} and the maximum difference is 13.13 {---} according to the exact F1 score, we find that models with a size smaller than 1B parameters are competitive for these tasks, all of which can be run on computers with a low-budget GPU or even without a GPU."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gongora-etal-2025-retuyt">
<titleInfo>
<title>RETUYT-INCO at BEA 2025 Shared Task: How Far Can Lightweight Models Go in AI-powered Tutor Evaluation?</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Góngora</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ignacio</namePart>
<namePart type="family">Sastre</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Robaina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ignacio</namePart>
<namePart type="family">Remersaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</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>In this paper, we present the RETUYT-INCO participation at the BEA 2025 shared task. Our participation was characterized by the decision of using relatively small models, with fewer than 1B parameters. This self-imposed restriction tries to represent the conditions in which many research groups or institutions are in the Global South, where computational power is not easily accessible due to its prohibitive cost. Even under this restrictive self-imposed setting, our models managed to stay competitive with the rest of teams that participated in the shared task. According to the exact F1 scores published by the organizers, our models had the following distances with respect to the winners: 6.46 in Track 1; 10.24 in Track 2; 7.85 in Track 3; 9.56 in Track 4; and 13.13 in Track 5. Considering that the minimum difference with a winner team is 6.46 points — and the maximum difference is 13.13 — according to the exact F1 score, we find that models with a size smaller than 1B parameters are competitive for these tasks, all of which can be run on computers with a low-budget GPU or even without a GPU.</abstract>
<identifier type="citekey">gongora-etal-2025-retuyt</identifier>
<identifier type="doi">10.18653/v1/2025.bea-1.89</identifier>
<location>
<url>https://aclanthology.org/2025.bea-1.89/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1135</start>
<end>1144</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T RETUYT-INCO at BEA 2025 Shared Task: How Far Can Lightweight Models Go in AI-powered Tutor Evaluation?
%A Góngora, Santiago
%A Sastre, Ignacio
%A Robaina, Santiago
%A Remersaro, Ignacio
%A Chiruzzo, Luis
%A Rosá, Aiala
%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 gongora-etal-2025-retuyt
%X In this paper, we present the RETUYT-INCO participation at the BEA 2025 shared task. Our participation was characterized by the decision of using relatively small models, with fewer than 1B parameters. This self-imposed restriction tries to represent the conditions in which many research groups or institutions are in the Global South, where computational power is not easily accessible due to its prohibitive cost. Even under this restrictive self-imposed setting, our models managed to stay competitive with the rest of teams that participated in the shared task. According to the exact F1 scores published by the organizers, our models had the following distances with respect to the winners: 6.46 in Track 1; 10.24 in Track 2; 7.85 in Track 3; 9.56 in Track 4; and 13.13 in Track 5. Considering that the minimum difference with a winner team is 6.46 points — and the maximum difference is 13.13 — according to the exact F1 score, we find that models with a size smaller than 1B parameters are competitive for these tasks, all of which can be run on computers with a low-budget GPU or even without a GPU.
%R 10.18653/v1/2025.bea-1.89
%U https://aclanthology.org/2025.bea-1.89/
%U https://doi.org/10.18653/v1/2025.bea-1.89
%P 1135-1144
Markdown (Informal)
[RETUYT-INCO at BEA 2025 Shared Task: How Far Can Lightweight Models Go in AI-powered Tutor Evaluation?](https://aclanthology.org/2025.bea-1.89/) (Góngora et al., BEA 2025)
ACL