---
title: "NLP-CIMAT at SemEval-2026 Task 9: LLM-Based One-Shot and"
description: "The authors address binary polarization detection for SemEval-2026 Task 9 (POLAR, Subtask 1). 30 references."
authors: ["Miriam Calderon-Reyes", "Fernando Sanchez-Vega", "Adrian Pastor Lopez Monroy"]
year: 2026
venue: "Proceedings of the 20th International Workshop on Semantic Evaluation (2026)"
source: "https://aclanthology.org/2026.semeval-1.362/"
doi: "10.18653/v1/2026.semeval-1.362"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/reyes-2026-nlp-cimat-semeval-2026-task/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/reyes-2026-nlp-cimat-semeval-2026-task/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/43/) / NLP-CIMAT at SemEval-2026 Task 9: LLM-Based One-Shot and Cross-Lingual Data Augmentation for Polarization Detection

# NLP-CIMAT at SemEval-2026 Task 9: LLM-Based One-Shot and Cross-Lingual Data Augmentation for Polarization Detection

**Authors:** Miriam Calderon-Reyes, [Fernando Sanchez-Vega](https://md.research.elamur.ai/free/en/authors/fernando-sanchez-vega/) and Adrian Pastor Lopez Monroy · **Year:** 2026 · **Venue:** [Proceedings of the 20th International Workshop on Semantic Evaluation (2026)](https://md.research.elamur.ai/free/en/venues/semeval/) ([SemEval 2026](https://md.research.elamur.ai/free/en/venues/semeval/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.semeval-1.362/) · [PDF](https://aclanthology.org/2026.semeval-1.362.pdf) · [DOI 10.18653/v1/2026.semeval-1.362](https://doi.org/10.18653/v1/2026.semeval-1.362) · [OpenAlex](https://openalex.org/W7166849560)

**Citations:** 0 citations (OpenAlex, 2026-10-14)

## Summary
The authors address binary polarization detection for SemEval-2026 Task 9 (POLAR, Subtask 1). In this task, annotated data is scarce and polarized language is often subtle. They focus mainly on Spanish and build a matching English system. To enlarge training data, they translate labeled POLAR texts from many other languages into the target language using the Google Cloud Translation API. They also prompt RigoChat 2 to produce informal, tweet-style Spanish texts on topics outside the original domains: sports and science/technology. These synthetic texts are kept only if a one-shot self-classification check confirms their labels. A greedy procedure adds each data source only if it raises F1. The classifiers are soft-voting ensembles: BETO with RigoBERTa 2.0 for Spanish, and BERT-large-uncased with RoBERTa-large for English. The Spanish system reaches macro F1 0.7869, about 0.016 below the winning team. The English system reaches 0.7939. The results suggest that translation-based augmentation works best between culturally close languages. Synthetic data helps only when its domain has clear group-versus-group conflict.

## Key points
- **Results and rankings:** Test macro F1 was 0.7869 for Spanish, equivalent to 7th place, and 0.7939 for English, ranked 21st. Only the English run appears on the leaderboard because of the submission policy.
- **Data selection:** Translated data came from up to 21 other POLAR languages. Greedy selection kept only a subset, for example English, Italian and German for Spanish, and Russian and German for English. Training sets grew from about 3.3k original examples to roughly 9.7k–13k.
- **Synthetic data generation:** Texts were produced with RigoChat-7b-v2 and filtered by self-consistency. Each text was classified five times at temperature 0.6 and kept only if label confidence was at least 0.65.
- **Domain effects:** Synthetic sports data improved results, while science data did not. The authors explain that sports discourse has a built-in "us vs. them" structure. Scientific disputes lack clear social groups, so this data pushes the model toward general sentiment.
- **Ethics and resources:** The authors warn that content translated across cultures may carry different harms, and that such models carry dual-use risks such as censorship. Code is released on GitHub (nlpcimat-at-POLAR).

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

Also on the byline: [Mathematics Research Center](https://ror.org/02nhmp827) · [Secretaría de Ciencia, Humanidades, Tecnología e Innovación](https://ror.org/059ex5q34).

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

🧭 Topics (1): [🌍 Multilingual & cross-lingual NLP](https://md.research.elamur.ai/free/en/topics/multilingual-nlp/) · 882 works

## Cite

Cite as: Miriam Calderon-Reyes, Fernando Sanchez-Vega and Adrian Pastor Lopez Monroy. 2026. NLP-CIMAT at SemEval-2026 Task 9: LLM-Based One-Shot and Cross-Lingual Data Augmentation for Polarization Detection. Proceedings of the 20th International Workshop on Semantic Evaluation (2026).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{calderonreyes2026nlp,
  title = {{NLP-CIMAT at SemEval-2026 Task 9: LLM-Based One-Shot and Cross-Lingual Data Augmentation for Polarization Detection}},
  author = {Miriam Calderon-Reyes, Fernando Sanchez-Vega and Adrian Pastor Lopez Monroy},
  booktitle = {Proceedings of the 20th International Workshop on Semantic Evaluation (2026)},
  year = {2026},
  doi = {10.18653/v1/2026.semeval-1.362},
  url = {https://doi.org/10.18653/v1/2026.semeval-1.362}
}
```

- [← previous NLG Evaluation: Past, Present, Future](https://md.research.elamur.ai/free/en/papers/reiter-2026-nlg-evaluation-past-present-future/)
- [next → NM at CRF Filling 2026: A Two-Stage LLM Pipeline for Clinical CRF Population](https://md.research.elamur.ai/free/en/papers/morabito-2026-nm-crf-filling-2026-two/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/43/)

## References

30 references, 14 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Christopher A. Bail, Lisa P. Argyle, Taylor W. Brown, John P. Bumpus, Haohan Chen, M. B. Fallin Hunzaker, Jaemin Lee, Marcus Mann, Friedolin Merhout, and Alexander Volfovsky. 2018. Exposure to opposing views on social media can increase political polarization. Proceedings of the National Academy of… [find](https://scholar.google.com/scholar?q=Christopher+A%2E+Bail%2C+Lisa+P%2E+Argyle%2C+Taylor+W%2E+Brown%2C+John+P%2E+Bumpus%2C+Haohan+Chen%2C+M%2E+B%2E+Fallin+Hunzaker%2C+Jaemin+Lee%2C+Marcus+Mann%2C+Friedolin+Merhout%2C+and+Alexander+Volfovsky%2E+2018%2E+Exposure+to+opposin)
2. Eytan Bakshy, Solomon Messing, and Lada A. Adamic. 2015. Exposure to ideologically diverse news and opinion on Facebook. Science, 348(6239):1130– 1132. [find](https://scholar.google.com/scholar?q=Eytan+Bakshy%2C+Solomon+Messing%2C+and+Lada+A%2E+Adamic%2E+2015%2E+Exposure+to+ideologically+diverse+news+and+opinion+on+Facebook%2E+Science%2C+348%286239%29%3A1130%E2%80%93+1132%2E)
3. Valerio Basile, Cristina Bosco, Elisabetta Fersini, Debora Nozza, Viviana Patti, Francisco Manuel Rangel Pardo, Paolo Rosso, and Manuela Sanguinetti. 2019. [SemEval-2019 task 5: Multilingual detection of hate speech against immigrants and women in Twitter](https://md.research.elamur.ai/free/en/papers/basile-2019-semeval-2019-task-5-multilingual/). In Proceedings of the 13th International Wor…
4. Emily M. Bender. 2019. The technical is political: Ethical considerations in NLP research. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Emily+M%2E+Bender%2E+2019%2E+The+technical+is+political%3A+Ethical+considerations+in+NLP+research%2E+In+Proceedings+of+the+57th+Annual+Meeting+of+the+Association+for+Computational+Linguistics%2C+Florence%2C+Italy%2E+)
5. Aaron Bramson, Patrick Grim, Daniel Singer, Steven Fisher, William Berger, Graham Sack, and Carissa Flocken. 2016. Disambiguation of social polarization concepts and measures. The Journal of Mathematical Sociology, 40:80–111. [find](https://scholar.google.com/scholar?q=Aaron+Bramson%2C+Patrick+Grim%2C+Daniel+Singer%2C+Steven+Fisher%2C+William+Berger%2C+Graham+Sack%2C+and+Carissa+Flocken%2E+2016%2E+Disambiguation+of+social+polarization+concepts+and+measures%2E+The+Journal+of+Mathemati)
6. José Cañete, Gabriel Chaperon, Rodrigo Fuentes, Jou-Hui Ho, Hojin Kang, and Jorge Pérez. 2023. Spanish pre-trained bert model and evaluation data. Preprint, arXiv:2308.02976. [find](https://scholar.google.com/scholar?q=Jos%C3%A9+Ca%C3%B1ete%2C+Gabriel+Chaperon%2C+Rodrigo+Fuentes%2C+Jou%2DHui+Ho%2C+Hojin+Kang%2C+and+Jorge+P%C3%A9rez%2E+2023%2E+Spanish+pre%2Dtrained+bert+model+and+evaluation+data%2E+Preprint%2C+arXiv%3A2308%2E02976%2E)
7. John Chung, Ece Kamar, and Saleema Amershi. 2023. [Increasing diversity while maintaining accuracy: Text data generation with large language models and human interventions](https://md.research.elamur.ai/free/en/papers/chung-2023-increasing-diversity-while-maintaining-accuracy/). In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 575–59…
8. Matteo Cinelli, Gianmarco Morales, Alessandro Galeazzi, Walter Quattrociocchi, and Michele Starnini. 2021. The echo chamber effect on social media. Proceedings of the National Academy of Sciences, 118:e2023301118. [find](https://scholar.google.com/scholar?q=Matteo+Cinelli%2C+Gianmarco+Morales%2C+Alessandro+Galeazzi%2C+Walter+Quattrociocchi%2C+and+Michele+Starnini%2E+2021%2E+The+echo+chamber+effect+on+social+media%2E+Proceedings+of+the+National+Academy+of+Sciences%2C+118)
9. Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2020. [Unsupervised cross-lingual representation learning at scale](https://md.research.elamur.ai/free/en/papers/conneau-2020-unsupervised-cross-lingual-representation-learning/). In Proceedings of the 58th Annual Meeting of the Association fo…
10. Thomas Davidson, Dana Warmsley, Michael Macy, and Ingmar Weber. 2017. [Automated hate speech detection and the problem of offensive language](https://md.research.elamur.ai/free/en/papers/davidson-2017-automated-hate-speech-detection-problem/). Preprint, arXiv:1703.04009.
11. Sergey Edunov, Myle Ott, Michael Auli, and David Grangier. 2018. Understanding back-translation at scale. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 489–500, Brussels, Belgium. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Sergey+Edunov%2C+Myle+Ott%2C+Michael+Auli%2C+and+David+Grangier%2E+2018%2E+Understanding+back%2Dtranslation+at+scale%2E+In+Proceedings+of+the+2018+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pag)
12. Marzieh Fadaee, Arianna Bisazza, and Christof Monz. 2017. [Data augmentation for low-resource neural machine translation](https://md.research.elamur.ai/free/en/papers/fadaee-2017-data-augmentation-low-resource-neural/). In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pages 567–573, Vancouver, Canada. Association for Computationa…
13. Steven Y. Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, and Eduard Hovy. 2021a. [A survey of data augmentation approaches for NLP](https://md.research.elamur.ai/free/en/papers/feng-2021-survey-data-augmentation-approaches-nlp/). In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 968–988, Online. Association for Computational Li…
14. Steven Y. Feng, Varun Gangal, Jason Wei, Sarath Chandar, Soroush Vosoughi, Teruko Mitamura, and Eduard Hovy. 2021b. [A survey of data augmentation approaches for NLP](https://md.research.elamur.ai/free/en/papers/feng-2021-survey-data-augmentation-approaches-nlp/). In Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pages 968–988, Online. Association for Computational Li…
15. Gonzalo Santamaría Gómez, Guillem García Subies, Pablo Gutiérrez Ruiz, Mario González Valero, Natàlia Fuertes, Helena Montoro Zamorano, Carmen Muñoz Sanz, Leire Rosado Plaza, Nuria Aldama García, David Betancur Sánchez, Kateryna Sushkova, Marta Guerrero Nieto, and Álvaro Barbero Jiménez. 2025. Rigoc… — [arXiv:2503.08188](https://arxiv.org/abs/2503.08188) [find](https://scholar.google.com/scholar?q=Gonzalo+Santamar%C3%ADa+G%C3%B3mez%2C+Guillem+Garc%C3%ADa+Subies%2C+Pablo+Guti%C3%A9rrez+Ruiz%2C+Mario+Gonz%C3%A1lez+Valero%2C+Nat%C3%A0lia+Fuertes%2C+Helena+Montoro+Zamorano%2C+Carmen+Mu%C3%B1oz+Sanz%2C+Leire+Rosado+Plaza%2C+Nuria+Aldama+Garc%C3%ADa%2C+Davi)
16. Pratik Joshi, Sebastin Santy, Amar Budhiraja, Kalika Bali, and Monojit Choudhury. 2020. [The state and fate of linguistic diversity and inclusion in the NLP world](https://md.research.elamur.ai/free/en/papers/joshi-2020-state-fate-linguistic-diversity-inclusion/). In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6282–6293, Online. Association for Comp…
17. Varun Kumar, Ashutosh Choudhary, and Eunah Cho. 2020. [Data augmentation using pre-trained transformer models](https://md.research.elamur.ai/free/en/papers/kumar-2020-data-augmentation-using-pre-trained/). In Proceedings of the 2nd Workshop on Life-long Learning for Spoken Language Systems, pages 18–26, Suzhou, China. Association for Computational Linguistics.
18. Alexandre Magueresse, Vincent Carles, and Evan Heetderks. 2020. Low-resource languages: A review of past work and future challenges. Preprint, arXiv:2006.07264. — [arXiv:2006.07264](https://arxiv.org/abs/2006.07264) [find](https://scholar.google.com/scholar?q=Alexandre+Magueresse%2C+Vincent+Carles%2C+and+Evan+Heetderks%2E+2020%2E+Low%2Dresource+languages%3A+A+review+of+past+work+and+future+challenges%2E+Preprint%2C+arXiv%3A2006%2E07264%2E+%E2%80%94+%5BarXiv%3A2006%2E07264%5D%28https%3A%2F%2Farxiv%2Eorg%2F)
19. Lilliana Mason. 2015. “i disrespectfully agree”: The differential effects of partisan sorting on social and issue polarization. American Journal of Political Science, 59(1):128–145. [find](https://scholar.google.com/scholar?q=Lilliana+Mason%2E+2015%2E+%E2%80%9Ci+disrespectfully+agree%E2%80%9D%3A+The+differential+effects+of+partisan+sorting+on+social+and+issue+polarization%2E+American+Journal+of+Political+Science%2C+59%281%29%3A128%E2%80%93145%2E)
20. Anders Giovanni Møller, Jacob Aarup Dalsgaard, Arianna Pera, and Luca Maria Aiello. 2024. The parrot dilemma: Human-labeled vs. llm-augmented data in classification tasks. Preprint, arXiv:2304.13861. [find](https://scholar.google.com/scholar?q=Anders+Giovanni+M%C3%B8ller%2C+Jacob+Aarup+Dalsgaard%2C+Arianna+Pera%2C+and+Luca+Maria+Aiello%2E+2024%2E+The+parrot+dilemma%3A+Human%2Dlabeled+vs%2E+llm%2Daugmented+data+in+classification+tasks%2E+Preprint%2C+arXiv%3A2304%2E13861%2E)
21. Usman Naseem, Robert Geislinger, Juan Ren, Sarah Kohail, Rudy Garrido Veliz, P Sam Sahil, Yiran Zhang, Marco Antonio Stranisci, Idris Abdulmumin, "Ozge Alacam, Cengiz Acar"urk, Aisha Jabr, Saba Anwar, Abinew Ali Ayele, Elena Tutubalina, Aung Kyaw Htet, Xintong Wang, Surendrabikram Thapa, Tanmoy Chak… — [SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization](https://md.research.elamur.ai/free/en/papers/naseem-2026-semeval-2026-task-9-detecting/)
22. Usman Naseem, Robert Geislinger, Juan Ren, Sarah Kohail, Rudy Garrido Veliz, P Sam Sahil, Yiran Zhang, Marco Antonio Stranisci, Idris Abdulmumin, Özge Alacam, Cengiz Acartürk, Aisha Jabr, Saba Anwar, Abinew Ali Ayele, Simona Frenda, Alessandra Teresa Cignarella, Elena Tutubalina, Oleg Rogov, Aung Ky… — [POLAR: A Benchmark for Multilingual, Multicultural, and Multi-Event Online Polarization](https://md.research.elamur.ai/free/en/papers/naseem-2026-polar-benchmark-multilingual-multicultural-multi/)
23. Eli Pariser. 2011. The Filter Bubble: What the Internet Is Hiding from You. Penguin Press, New York, NY. [find](https://scholar.google.com/scholar?q=Eli+Pariser%2E+2011%2E+The+Filter+Bubble%3A+What+the+Internet+Is+Hiding+from+You%2E+Penguin+Press%2C+New+York%2C+NY%2E)
24. Walter Quattrociocchi, Antonio Scala, and C. Sunstein. 2016. Echo chambers on facebook. SSRN Electronic Journal. [find](https://scholar.google.com/scholar?q=Walter+Quattrociocchi%2C+Antonio+Scala%2C+and+C%2E+Sunstein%2E+2016%2E+Echo+chambers+on+facebook%2E+SSRN+Electronic+Journal%2E)
25. Paul Röttger, Bertie Vidgen, Dong Nguyen, Zeerak Waseem, Helen Margetts, and Janet Pierrehumbert. 2021. [HateCheck: Functional tests for hate speech detection models](https://md.research.elamur.ai/free/en/papers/rottger-2021-hatecheck-functional-tests-hate-speech/). In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference…
26. Rico Sennrich, Barry Haddow, and Alexandra Birch. 2016. Improving neural machine translation models with monolingual data. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 86–96, Berlin, Germany. Association for Computational L… [find](https://scholar.google.com/scholar?q=Rico+Sennrich%2C+Barry+Haddow%2C+and+Alexandra+Birch%2E+2016%2E+Improving+neural+machine+translation+models+with+monolingual+data%2E+In+Proceedings+of+the+54th+Annual+Meeting+of+the+Association+for+Computationa)
27. Chen Sun, Abhinav Shrivastava, Saurabh Singh, and Abhinav Gupta. 2017. [Revisiting unreasonable effectiveness of data in deep learning era](https://md.research.elamur.ai/free/en/papers/sun-2017-revisiting-unreasonable-effectiveness-data-deep/). Preprint, arXiv:1707.02968.
28. Cass R. Sunstein. 2017. \#Republic: Divided Democracy in the Age of Social Media. Princeton University Press, Princeton, NJ. [find](https://scholar.google.com/scholar?q=Cass+R%2E+Sunstein%2E+2017%2E+%5C%23Republic%3A+Divided+Democracy+in+the+Age+of+Social+Media%2E+Princeton+University+Press%2C+Princeton%2C+NJ%2E)
29. Jason Wei and Kai Zou. 2019. [EDA: Easy data augmentation techniques for boosting performance on text classification tasks](https://md.research.elamur.ai/free/en/papers/wei-2019-eda-easy-data-augmentation-techniques/). In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP…
30. Chenxi Whitehouse, Monojit Choudhury, and Alham Fikri Aji. 2023. LLM-powered data augmentation for enhanced cross-lingual performance. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 671– 686, Singapore. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Chenxi+Whitehouse%2C+Monojit+Choudhury%2C+and+Alham+Fikri+Aji%2E+2023%2E+LLM%2Dpowered+data+augmentation+for+enhanced+cross%2Dlingual+performance%2E+In+Proceedings+of+the+2023+Conference+on+Empirical+Methods+in+Nat)

*Updated 2 November 2026*