@inproceedings{madera-espindola-etal-2025-transformers,
title = "Transformers and Large Language Models for Hope Speech Detection A Multilingual Approach",
author = "Madera-Esp{\'i}ndola, Diana Patricia and
Caballero-Dom{\'i}nguez, Zoe and
Ram{\'i}rez-Mac{\'i}as, Valeria J. and
Butt, Sabur and
Ceballos, Hector G.",
editor = "Picazo-Izquierdo, Alicia and
Estevanell-Valladares, Ernesto Luis and
Mitkov, Ruslan and
Guillena, Rafael Mu{\~n}oz and
Cerd{\'a}, Ra{\'u}l Garc{\'i}a",
booktitle = "Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models",
month = sep,
year = "2025",
address = "Varna, Bulgaria",
publisher = "INCOMA Ltd., Shoumen, Bulgaria",
url = "https://aclanthology.org/2025.r2lm-1.8/",
pages = "67--76",
abstract = "With the rise of Generative AI (GenAI) models in recent years, it is necessary to understand how they performed compared with other Deep Learning techniques, across tasks and across different languages. In this study, we benchmark ChatGPT-4 and XML-RoBERTa, a multilingual transformer-based model, as part of the Multilingual Binary and Multiclass Hope Speech Detection within the PolyHope-M 2025 competition. Furthermore, we explored prompting techniques and data augmentation to determine which approach yields the best performance. In our experiments, XML-RoBERTa frequently outperformed ChatGPT-4. It also attained F1 scores of 0.86 for English, 0.83 for Spanish, 0.86 for German, and 0.94 for Urdu in Task 1, while achieving 0.73 for English, 0.70 for Spanish, 0.69 for German, and 0.60 for Urdu in Task 2."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="madera-espindola-etal-2025-transformers">
<titleInfo>
<title>Transformers and Large Language Models for Hope Speech Detection A Multilingual Approach</title>
</titleInfo>
<name type="personal">
<namePart type="given">Diana</namePart>
<namePart type="given">Patricia</namePart>
<namePart type="family">Madera-Espíndola</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zoe</namePart>
<namePart type="family">Caballero-Domínguez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valeria</namePart>
<namePart type="given">J</namePart>
<namePart type="family">Ramírez-Macías</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sabur</namePart>
<namePart type="family">Butt</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hector</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Ceballos</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-09</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Alicia</namePart>
<namePart type="family">Picazo-Izquierdo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ernesto</namePart>
<namePart type="given">Luis</namePart>
<namePart type="family">Estevanell-Valladares</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruslan</namePart>
<namePart type="family">Mitkov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rafael</namePart>
<namePart type="given">Muñoz</namePart>
<namePart type="family">Guillena</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raúl</namePart>
<namePart type="given">García</namePart>
<namePart type="family">Cerdá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>INCOMA Ltd., Shoumen, Bulgaria</publisher>
<place>
<placeTerm type="text">Varna, Bulgaria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the rise of Generative AI (GenAI) models in recent years, it is necessary to understand how they performed compared with other Deep Learning techniques, across tasks and across different languages. In this study, we benchmark ChatGPT-4 and XML-RoBERTa, a multilingual transformer-based model, as part of the Multilingual Binary and Multiclass Hope Speech Detection within the PolyHope-M 2025 competition. Furthermore, we explored prompting techniques and data augmentation to determine which approach yields the best performance. In our experiments, XML-RoBERTa frequently outperformed ChatGPT-4. It also attained F1 scores of 0.86 for English, 0.83 for Spanish, 0.86 for German, and 0.94 for Urdu in Task 1, while achieving 0.73 for English, 0.70 for Spanish, 0.69 for German, and 0.60 for Urdu in Task 2.</abstract>
<identifier type="citekey">madera-espindola-etal-2025-transformers</identifier>
<location>
<url>https://aclanthology.org/2025.r2lm-1.8/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>67</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transformers and Large Language Models for Hope Speech Detection A Multilingual Approach
%A Madera-Espíndola, Diana Patricia
%A Caballero-Domínguez, Zoe
%A Ramírez-Macías, Valeria J.
%A Butt, Sabur
%A Ceballos, Hector G.
%Y Picazo-Izquierdo, Alicia
%Y Estevanell-Valladares, Ernesto Luis
%Y Mitkov, Ruslan
%Y Guillena, Rafael Muñoz
%Y Cerdá, Raúl García
%S Proceedings of the First Workshop on Comparative Performance Evaluation: From Rules to Language Models
%D 2025
%8 September
%I INCOMA Ltd., Shoumen, Bulgaria
%C Varna, Bulgaria
%F madera-espindola-etal-2025-transformers
%X With the rise of Generative AI (GenAI) models in recent years, it is necessary to understand how they performed compared with other Deep Learning techniques, across tasks and across different languages. In this study, we benchmark ChatGPT-4 and XML-RoBERTa, a multilingual transformer-based model, as part of the Multilingual Binary and Multiclass Hope Speech Detection within the PolyHope-M 2025 competition. Furthermore, we explored prompting techniques and data augmentation to determine which approach yields the best performance. In our experiments, XML-RoBERTa frequently outperformed ChatGPT-4. It also attained F1 scores of 0.86 for English, 0.83 for Spanish, 0.86 for German, and 0.94 for Urdu in Task 1, while achieving 0.73 for English, 0.70 for Spanish, 0.69 for German, and 0.60 for Urdu in Task 2.
%U https://aclanthology.org/2025.r2lm-1.8/
%P 67-76
Markdown (Informal)
[Transformers and Large Language Models for Hope Speech Detection A Multilingual Approach](https://aclanthology.org/2025.r2lm-1.8/) (Madera-Espíndola et al., R2LM 2025)
ACL