@inproceedings{durand-etal-2026-pfr821,
title = "pfr821 at {S}em{E}val-2026 Task 9: Multilingual Polarization Detection via Hybrid {XLM}-{R}o{BERT}a with Targeted Data Augmentation and Imbalance-Aware Training",
author = "Durand, Antoine and
Hamon, R{\'e}mi and
Pereira, Matthieu and
Boucneau, Nathan and
Cintra, Paul",
editor = "Kochmar, Ekaterina and
Ghosh, Debanjan and
North, Kai and
Komachi, Mamoru",
booktitle = "Proceedings of the 20th {I}nternational {W}orkshop on {S}emantic {E}valuation (2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.semeval-1.160/",
pages = "1169--1174",
ISBN = "979-8-89176-414-9",
abstract = "This paper describes HYPOLDET, the system submitted by team pfr821 to SemEval-2026 Task 9 (Polarization Detection, Subtask 1), a binary classification task over 22 typologically diverse languages. Our approach combines three complementary contributions. We first extend XLM-RoBERTa-Large with a custom transformer encoder layer and a learned attention-based pooling mechanism (Hybrid Architecture), allowing the model to aggregate token-level signals beyond the [CLS] representation. We then augment training data through a targeted LLM-based synthetic generation pipeline (Grok API), producing culturally grounded examples for low-resource and imbalanced languages. Finally, we address class imbalance at the training level through an imbalance-aware regime combining a per-language balanced batch sampler, weighted focal loss, and label smoothing. Our best single model achieves an unweighted macro-averaged F1 of 0.796, and a lightweight ensemble reaches 0.798, ranking in the top 10 for 7 languages and 2nd place for Hausa."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="durand-etal-2026-pfr821">
<titleInfo>
<title>pfr821 at SemEval-2026 Task 9: Multilingual Polarization Detection via Hybrid XLM-RoBERTa with Targeted Data Augmentation and Imbalance-Aware Training</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Durand</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rémi</namePart>
<namePart type="family">Hamon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthieu</namePart>
<namePart type="family">Pereira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Boucneau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Cintra</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 20th International Workshop on Semantic Evaluation (2026)</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">Debanjan</namePart>
<namePart type="family">Ghosh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">North</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mamoru</namePart>
<namePart type="family">Komachi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-414-9</identifier>
</relatedItem>
<abstract>This paper describes HYPOLDET, the system submitted by team pfr821 to SemEval-2026 Task 9 (Polarization Detection, Subtask 1), a binary classification task over 22 typologically diverse languages. Our approach combines three complementary contributions. We first extend XLM-RoBERTa-Large with a custom transformer encoder layer and a learned attention-based pooling mechanism (Hybrid Architecture), allowing the model to aggregate token-level signals beyond the [CLS] representation. We then augment training data through a targeted LLM-based synthetic generation pipeline (Grok API), producing culturally grounded examples for low-resource and imbalanced languages. Finally, we address class imbalance at the training level through an imbalance-aware regime combining a per-language balanced batch sampler, weighted focal loss, and label smoothing. Our best single model achieves an unweighted macro-averaged F1 of 0.796, and a lightweight ensemble reaches 0.798, ranking in the top 10 for 7 languages and 2nd place for Hausa.</abstract>
<identifier type="citekey">durand-etal-2026-pfr821</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.160/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1169</start>
<end>1174</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T pfr821 at SemEval-2026 Task 9: Multilingual Polarization Detection via Hybrid XLM-RoBERTa with Targeted Data Augmentation and Imbalance-Aware Training
%A Durand, Antoine
%A Hamon, Rémi
%A Pereira, Matthieu
%A Boucneau, Nathan
%A Cintra, Paul
%Y Kochmar, Ekaterina
%Y Ghosh, Debanjan
%Y North, Kai
%Y Komachi, Mamoru
%S Proceedings of the 20th International Workshop on Semantic Evaluation (2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-414-9
%F durand-etal-2026-pfr821
%X This paper describes HYPOLDET, the system submitted by team pfr821 to SemEval-2026 Task 9 (Polarization Detection, Subtask 1), a binary classification task over 22 typologically diverse languages. Our approach combines three complementary contributions. We first extend XLM-RoBERTa-Large with a custom transformer encoder layer and a learned attention-based pooling mechanism (Hybrid Architecture), allowing the model to aggregate token-level signals beyond the [CLS] representation. We then augment training data through a targeted LLM-based synthetic generation pipeline (Grok API), producing culturally grounded examples for low-resource and imbalanced languages. Finally, we address class imbalance at the training level through an imbalance-aware regime combining a per-language balanced batch sampler, weighted focal loss, and label smoothing. Our best single model achieves an unweighted macro-averaged F1 of 0.796, and a lightweight ensemble reaches 0.798, ranking in the top 10 for 7 languages and 2nd place for Hausa.
%U https://aclanthology.org/2026.semeval-1.160/
%P 1169-1174
Markdown (Informal)
[pfr821 at SemEval-2026 Task 9: Multilingual Polarization Detection via Hybrid XLM-RoBERTa with Targeted Data Augmentation and Imbalance-Aware Training](https://aclanthology.org/2026.semeval-1.160/) (Durand et al., SemEval 2026)
ACL