PulseAugur
LIVE 08:13:14
research · [7 sources] ·
0
research

Teams leverage LLMs and ensemble methods for multilingual online polarization detection at SemEval-2026

By PulseAugur Editorial · Summary by gemini-2.5-flash-lite from 7 sources

Researchers have developed systems for SemEval-2026 Task 9, a multilingual polarization detection challenge across 22 languages. One approach fine-tuned Gemma 3 models using Low-Rank Adaptation (LoRA) and augmented data generated by GPT-4o-mini, achieving a mean macro-F1 of 0.811 and ranking second overall. Another method focused on fine-tuning mid-size LLMs with QLoRA and data augmentation techniques like anonymization and homoglyphing to improve robustness. AI

Summary written by gemini-2.5-flash-lite from 7 sources. How we write summaries →

IMPACT Demonstrates advanced LLM fine-tuning techniques for multilingual NLP tasks, potentially improving online content moderation.

RANK_REASON Academic papers detailing methods for a specific NLP task.

Read on arXiv cs.CL →

COVERAGE [7]

  1. arXiv cs.CL TIER_1 · Fengze Guo (University of T\"ubingen), Yue Chang (University of T\"ubingen) ·

    YEZE at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization via Heterogeneous Ensembling

    arXiv:2605.06231v1 Announce Type: new Abstract: This paper presents our system for SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization, which identifies polarized social media content in 22 languages through three subtasks: binary detecti…

  2. arXiv cs.CL TIER_1 · Yue Chang ·

    YEZE at SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization via Heterogeneous Ensembling

    This paper presents our system for SemEval-2026 Task 9: Detecting Multilingual, Multicultural and Multievent Online Polarization, which identifies polarized social media content in 22 languages through three subtasks: binary detection, target classification, and manifestation ide…

  3. arXiv cs.LG TIER_1 · Srikar Kashyap Pulipaka ·

    PSK at SemEval-2026 Task 9: Multilingual Polarization Detection Using Ensemble Gemma Models with Synthetic Data Augmentation

    arXiv:2605.05159v1 Announce Type: cross Abstract: We present our system for SemEval-2026 Task 9: Multilingual Polarization Detection, a binary classification task spanning 22 languages. Our approach fine-tunes separate Gemma~3 models (12B and 27B parameters) per language using Lo…

  4. arXiv cs.CL TIER_1 · Srikar Kashyap Pulipaka ·

    PSK at SemEval-2026 Task 9: Multilingual Polarization Detection Using Ensemble Gemma Models with Synthetic Data Augmentation

    We present our system for SemEval-2026 Task 9: Multilingual Polarization Detection, a binary classification task spanning 22 languages. Our approach fine-tunes separate Gemma~3 models (12B and 27B parameters) per language using Low-Rank Adaptation (LoRA), augmented with synthetic…

  5. Hugging Face Daily Papers TIER_1 ·

    PSK at SemEval-2026 Task 9: Multilingual Polarization Detection Using Ensemble Gemma Models with Synthetic Data Augmentation

    We present our system for SemEval-2026 Task 9: Multilingual Polarization Detection, a binary classification task spanning 22 languages. Our approach fine-tunes separate Gemma~3 models (12B and 27B parameters) per language using Low-Rank Adaptation (LoRA), augmented with synthetic…

  6. arXiv cs.CL TIER_1 · Dominik Macko, Alok Debnath, Jakub Simko ·

    mdok-style at SemEval-2026 Task 9: Finetuning LLMs for Multilingual Polarization Detection

    arXiv:2605.02695v1 Announce Type: new Abstract: SemEval-2026 Task 9 is focused on multilingual polarization detection. Specifically, it covers the identification of multilingual, multicultural and multievent polarization along three axes (in subtasks), namely detection, type, and…

  7. arXiv cs.CL TIER_1 · Jakub Simko ·

    mdok-style at SemEval-2026 Task 9: Finetuning LLMs for Multilingual Polarization Detection

    SemEval-2026 Task 9 is focused on multilingual polarization detection. Specifically, it covers the identification of multilingual, multicultural and multievent polarization along three axes (in subtasks), namely detection, type, and manifestation. Online polarization presents a c…

RELATED ENTITIES

RELATED TOPICS