@inproceedings{grandy-khir-2026-poldeck,
title = "{P}ol{D}eck at {S}em{E}val-2026 Task 9: Multilingual Online Polarization Detection via Hybrid Model Ensembling and Data Augmentation",
author = "Grandy, Ben and
Khir, Daniel",
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-1.120/",
pages = "879--885",
ISBN = "979-8-89176-414-9",
abstract = "In this paper, we address SemEval 2026 Task 9: Multilingual Online Polarization Detection. We present our hybrid ensemble framework, integrating few-shot prompting with Qwen3-30B, a native multilingual XLM-R encoder, and a translation-augmented DeBERTa encoder. To mitigate label imbalance, we implement a multi-stage augmentation pipeline leveraging LLMs for synthetic paraphrasing and cross-lingual translation. Our system ranked in the Top 10 on the English and German leaderboards, proving that integrating both high-capacity monolingual models and flexible multilingual models in a holistic system is a viable method for detecting online polarization. Our code is available on GitHub."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="grandy-khir-2026-poldeck">
<titleInfo>
<title>PolDeck at SemEval-2026 Task 9: Multilingual Online Polarization Detection via Hybrid Model Ensembling and Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Grandy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Khir</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>In this paper, we address SemEval 2026 Task 9: Multilingual Online Polarization Detection. We present our hybrid ensemble framework, integrating few-shot prompting with Qwen3-30B, a native multilingual XLM-R encoder, and a translation-augmented DeBERTa encoder. To mitigate label imbalance, we implement a multi-stage augmentation pipeline leveraging LLMs for synthetic paraphrasing and cross-lingual translation. Our system ranked in the Top 10 on the English and German leaderboards, proving that integrating both high-capacity monolingual models and flexible multilingual models in a holistic system is a viable method for detecting online polarization. Our code is available on GitHub.</abstract>
<identifier type="citekey">grandy-khir-2026-poldeck</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.120/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>879</start>
<end>885</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PolDeck at SemEval-2026 Task 9: Multilingual Online Polarization Detection via Hybrid Model Ensembling and Data Augmentation
%A Grandy, Ben
%A Khir, Daniel
%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 grandy-khir-2026-poldeck
%X In this paper, we address SemEval 2026 Task 9: Multilingual Online Polarization Detection. We present our hybrid ensemble framework, integrating few-shot prompting with Qwen3-30B, a native multilingual XLM-R encoder, and a translation-augmented DeBERTa encoder. To mitigate label imbalance, we implement a multi-stage augmentation pipeline leveraging LLMs for synthetic paraphrasing and cross-lingual translation. Our system ranked in the Top 10 on the English and German leaderboards, proving that integrating both high-capacity monolingual models and flexible multilingual models in a holistic system is a viable method for detecting online polarization. Our code is available on GitHub.
%U https://aclanthology.org/2026.semeval-1.120/
%P 879-885
Markdown (Informal)
[PolDeck at SemEval-2026 Task 9: Multilingual Online Polarization Detection via Hybrid Model Ensembling and Data Augmentation](https://aclanthology.org/2026.semeval-1.120/) (Grandy & Khir, SemEval 2026)
ACL