@inproceedings{rabbani-etal-2025-hoax,
title = "Hoax Terminators@{LT}-{EDI} 2025: {C}har{BERT}{'}s dominance over {LLM} Models in the Detection of Racial Hoaxes in Code-Mixed {H}indi-{E}nglish Social Media Data",
author = "Rabbani, Abrar Hafiz and
Droba, Diganta Das and
Labib, Momtazul Arefin and
Rahman, Samia and
Murad, Hasan",
editor = "Gkirtzou, Katerina and
{\v{Z}}itnik, Slavko and
Gracia, Jorge and
Gromann, Dagmar and
di Buono, Maria Pia and
Monti, Johanna and
Ionov, Maxim",
booktitle = "Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion",
month = sep,
year = "2025",
address = "Naples, Italy",
publisher = "Unior Press",
url = "https://aclanthology.org/2025.ltedi-1.27/",
pages = "160--171",
ISBN = "978-88-6719-334-9",
abstract = "This paper presents our system for the LT-EDI 2025 Shared Task on Racial Hoax Detection, addressing the critical challenge of identifying racially charged misinformation in code-mixed Hindi-English (Hinglish) social media{---}a low-resource, linguistically complex domain with real-world impact. We adopt a two-pronged strategy, independently fine-tuning a transformer-based model and a large language model. CharBERT was optimized using Optuna, while XLM-RoBERTa and DistilBERT were fine-tuned for the classification task. FLAN-T5-base was fine-tuned with SMOTE-based oversampling, semantic-preserving back translation, and prompt engineering, whereas LLaMA was used solely for inference. Our preprocessing included Hinglish-specific normalization, noise reduction, sentiment-aware corrections and a custom weighted loss to emphasize the minority Hoax class. Despite using FLAN-T5-base due to resource limits, our models performed well. CharBERT achieved a macro F1 of 0.70 and FLAN-T5 followed at 0.69, both outperforming baselines like DistilBERT and LLaMA-3.2-1B. Our submission ranked 4th of 11 teams, underscoring the promise of our approach for scalable misinformation detection in code-switched contexts. Future work will explore larger LLMs, adversarial training and context-aware decoding."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rabbani-etal-2025-hoax">
<titleInfo>
<title>Hoax Terminators@LT-EDI 2025: CharBERT’s dominance over LLM Models in the Detection of Racial Hoaxes in Code-Mixed Hindi-English Social Media Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abrar</namePart>
<namePart type="given">Hafiz</namePart>
<namePart type="family">Rabbani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diganta</namePart>
<namePart type="given">Das</namePart>
<namePart type="family">Droba</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Momtazul</namePart>
<namePart type="given">Arefin</namePart>
<namePart type="family">Labib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Samia</namePart>
<namePart type="family">Rahman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hasan</namePart>
<namePart type="family">Murad</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 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion</title>
</titleInfo>
<name type="personal">
<namePart type="given">Katerina</namePart>
<namePart type="family">Gkirtzou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Slavko</namePart>
<namePart type="family">Žitnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jorge</namePart>
<namePart type="family">Gracia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dagmar</namePart>
<namePart type="family">Gromann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="given">Pia</namePart>
<namePart type="family">di Buono</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Johanna</namePart>
<namePart type="family">Monti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maxim</namePart>
<namePart type="family">Ionov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Unior Press</publisher>
<place>
<placeTerm type="text">Naples, Italy</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">978-88-6719-334-9</identifier>
</relatedItem>
<abstract>This paper presents our system for the LT-EDI 2025 Shared Task on Racial Hoax Detection, addressing the critical challenge of identifying racially charged misinformation in code-mixed Hindi-English (Hinglish) social media—a low-resource, linguistically complex domain with real-world impact. We adopt a two-pronged strategy, independently fine-tuning a transformer-based model and a large language model. CharBERT was optimized using Optuna, while XLM-RoBERTa and DistilBERT were fine-tuned for the classification task. FLAN-T5-base was fine-tuned with SMOTE-based oversampling, semantic-preserving back translation, and prompt engineering, whereas LLaMA was used solely for inference. Our preprocessing included Hinglish-specific normalization, noise reduction, sentiment-aware corrections and a custom weighted loss to emphasize the minority Hoax class. Despite using FLAN-T5-base due to resource limits, our models performed well. CharBERT achieved a macro F1 of 0.70 and FLAN-T5 followed at 0.69, both outperforming baselines like DistilBERT and LLaMA-3.2-1B. Our submission ranked 4th of 11 teams, underscoring the promise of our approach for scalable misinformation detection in code-switched contexts. Future work will explore larger LLMs, adversarial training and context-aware decoding.</abstract>
<identifier type="citekey">rabbani-etal-2025-hoax</identifier>
<location>
<url>https://aclanthology.org/2025.ltedi-1.27/</url>
</location>
<part>
<date>2025-09</date>
<extent unit="page">
<start>160</start>
<end>171</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Hoax Terminators@LT-EDI 2025: CharBERT’s dominance over LLM Models in the Detection of Racial Hoaxes in Code-Mixed Hindi-English Social Media Data
%A Rabbani, Abrar Hafiz
%A Droba, Diganta Das
%A Labib, Momtazul Arefin
%A Rahman, Samia
%A Murad, Hasan
%Y Gkirtzou, Katerina
%Y Žitnik, Slavko
%Y Gracia, Jorge
%Y Gromann, Dagmar
%Y di Buono, Maria Pia
%Y Monti, Johanna
%Y Ionov, Maxim
%S Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion
%D 2025
%8 September
%I Unior Press
%C Naples, Italy
%@ 978-88-6719-334-9
%F rabbani-etal-2025-hoax
%X This paper presents our system for the LT-EDI 2025 Shared Task on Racial Hoax Detection, addressing the critical challenge of identifying racially charged misinformation in code-mixed Hindi-English (Hinglish) social media—a low-resource, linguistically complex domain with real-world impact. We adopt a two-pronged strategy, independently fine-tuning a transformer-based model and a large language model. CharBERT was optimized using Optuna, while XLM-RoBERTa and DistilBERT were fine-tuned for the classification task. FLAN-T5-base was fine-tuned with SMOTE-based oversampling, semantic-preserving back translation, and prompt engineering, whereas LLaMA was used solely for inference. Our preprocessing included Hinglish-specific normalization, noise reduction, sentiment-aware corrections and a custom weighted loss to emphasize the minority Hoax class. Despite using FLAN-T5-base due to resource limits, our models performed well. CharBERT achieved a macro F1 of 0.70 and FLAN-T5 followed at 0.69, both outperforming baselines like DistilBERT and LLaMA-3.2-1B. Our submission ranked 4th of 11 teams, underscoring the promise of our approach for scalable misinformation detection in code-switched contexts. Future work will explore larger LLMs, adversarial training and context-aware decoding.
%U https://aclanthology.org/2025.ltedi-1.27/
%P 160-171
Markdown (Informal)
[Hoax Terminators@LT-EDI 2025: CharBERT’s dominance over LLM Models in the Detection of Racial Hoaxes in Code-Mixed Hindi-English Social Media Data](https://aclanthology.org/2025.ltedi-1.27/) (Rabbani et al., LTEDI 2025)
ACL
- Abrar Hafiz Rabbani, Diganta Das Droba, Momtazul Arefin Labib, Samia Rahman, and Hasan Murad. 2025. Hoax Terminators@LT-EDI 2025: CharBERT’s dominance over LLM Models in the Detection of Racial Hoaxes in Code-Mixed Hindi-English Social Media Data. In Proceedings of the 5th Conference on Language, Data and Knowledge: Fifth Workshop on Language Technology for Equality, Diversity, Inclusion, pages 160–171, Naples, Italy. Unior Press.