@inproceedings{calderon-reyes-etal-2026-nlp,
title = "{NLP}-{CIMAT} at {S}em{E}val-2026 Task 9: {LLM}-Based One-Shot and Cross-Lingual Data Augmentation for Polarization Detection",
author = "Calderon-Reyes, Miriam and
Sanchez-Vega, Fernando and
Lopez Monroy, Adrian Pastor",
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-1.362/",
pages = "2886--2893",
ISBN = "979-8-89176-414-9",
abstract = "This paper describes our participation in SemEval 2026 Task 9: Multilingual Text Polarization. The task requires estimating polarization levels across languages, where linguistic variability and limited annotated data pose significant challenges. To address data scarcity, we propose a pipeline that combines cross-lingual translation, synthetic data augmentation via LLMs, and domain-specific pre-trained models. Our approach leverages the hypothesis that polarization signals can transfer across languages without substantial loss of semantic alignment, enabling effective data augmentation through translation. Notably, one-shot synthetic example generation emerges as a viable strategy for enriching training data in topic-specific scenarios. Experimental results demonstrate high stability and competitive performance, achieving a macro F1-score of 0.7869 for Spanish and 0.7939 for English on the test set, ranking 21th on the official English leaderboard, while our Spanish results are competitive with top-performing systems, corresponding to 7th place."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="calderon-reyes-etal-2026-nlp">
<titleInfo>
<title>NLP-CIMAT at SemEval-2026 Task 9: LLM-Based One-Shot and Cross-Lingual Data Augmentation for Polarization Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Miriam</namePart>
<namePart type="family">Calderon-Reyes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fernando</namePart>
<namePart type="family">Sanchez-Vega</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Adrian</namePart>
<namePart type="given">Pastor</namePart>
<namePart type="family">Lopez Monroy</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 our participation in SemEval 2026 Task 9: Multilingual Text Polarization. The task requires estimating polarization levels across languages, where linguistic variability and limited annotated data pose significant challenges. To address data scarcity, we propose a pipeline that combines cross-lingual translation, synthetic data augmentation via LLMs, and domain-specific pre-trained models. Our approach leverages the hypothesis that polarization signals can transfer across languages without substantial loss of semantic alignment, enabling effective data augmentation through translation. Notably, one-shot synthetic example generation emerges as a viable strategy for enriching training data in topic-specific scenarios. Experimental results demonstrate high stability and competitive performance, achieving a macro F1-score of 0.7869 for Spanish and 0.7939 for English on the test set, ranking 21th on the official English leaderboard, while our Spanish results are competitive with top-performing systems, corresponding to 7th place.</abstract>
<identifier type="citekey">calderon-reyes-etal-2026-nlp</identifier>
<location>
<url>https://aclanthology.org/2026.semeval-1.362/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>2886</start>
<end>2893</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLP-CIMAT at SemEval-2026 Task 9: LLM-Based One-Shot and Cross-Lingual Data Augmentation for Polarization Detection
%A Calderon-Reyes, Miriam
%A Sanchez-Vega, Fernando
%A Lopez Monroy, Adrian Pastor
%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 calderon-reyes-etal-2026-nlp
%X This paper describes our participation in SemEval 2026 Task 9: Multilingual Text Polarization. The task requires estimating polarization levels across languages, where linguistic variability and limited annotated data pose significant challenges. To address data scarcity, we propose a pipeline that combines cross-lingual translation, synthetic data augmentation via LLMs, and domain-specific pre-trained models. Our approach leverages the hypothesis that polarization signals can transfer across languages without substantial loss of semantic alignment, enabling effective data augmentation through translation. Notably, one-shot synthetic example generation emerges as a viable strategy for enriching training data in topic-specific scenarios. Experimental results demonstrate high stability and competitive performance, achieving a macro F1-score of 0.7869 for Spanish and 0.7939 for English on the test set, ranking 21th on the official English leaderboard, while our Spanish results are competitive with top-performing systems, corresponding to 7th place.
%U https://aclanthology.org/2026.semeval-1.362/
%P 2886-2893
Markdown (Informal)
[NLP-CIMAT at SemEval-2026 Task 9: LLM-Based One-Shot and Cross-Lingual Data Augmentation for Polarization Detection](https://aclanthology.org/2026.semeval-1.362/) (Calderon-Reyes et al., SemEval 2026)
ACL