Skip to content
Preprint

N\"urnberg NLP @ GermEval Shared Task 2026: Harmful Content Detection in German Social Media through Error-Independent LLM Voters

Aug 2026 · 1 citation · 38 references
Computer Science

TL;DR

The GermEval 2026 shared task scores its detection in four subtasks in a per-subtask nine-voter ensemble spanning three orthogonal axes: LLM, training method and class scope, placing first on all four subtasks.

Abstract

Harmful content in German social media does real-world damage, from calls to action to criminal defamation. The GermEval 2026 shared task scores its detection in four subtasks. The technical challenge is a severe class imbalance. The harmful classes are rare and share surface language with the dominant majority class, yet under macro-F1 they decide the score. The decisive lever is then not a stronger single model but error independence. This insight becomes a per-subtask nine-voter ensemble spanning three orthogonal axes: LLM, training method and class scope. Selected mainly on internal cross-validation, the system reaches macro-F1 of 89.56 (C2A), 71.63 (DBO), 54.84 (VIO) and 83.02 (DEF) on the hidden test set, placing first on all four subtasks.

View source

Similar papers

IGT @ FinMMEval 2026 Task 2: Question-Type Prompting with Targeted Extraction for Multilingual Financial QA

The IGT system for PolyFiQA Task 2 of the FinMMEval Lab at CLEF 2026, a multilingual financial question answering task over English SEC filings and multilingual news articles for four companies, achieves development ROUGE-1 approximately 0.395, a 60% relative improvement over a generic RAG baseline.

Yu-Wen Chiu · 1 citation
Preprint Aug 2026

EVIL-Detect for NLPCC 2026 Shared Task 6: LLM-Generated Text Detection

EVIL-Detect, a multi-signal ensemble framework with conflict-aware fusion for NLPCC 2026 Shared Task 6, improves robustness under strong out-of-distribution shifts, achieving a macro-F1 score of 0.8888 and ranking first in the official evaluation.

Hong-Rui Bao, Hangyu Rong, Zhuo Wang et al. · 1 citation

Flauschgummi at GermEval 2025 Shared Task on Candy Speech Detection: Sentiment Analysis and Classification of Online Comments

This work examines the effectiveness of stacking traditional machine learning techniques like Logistic Regression, k-Nearest Neighbors, Random Forest, Multi-Layer Perceptron, Support Vector Classifier and simple word counting and compares them to BERT, a powerful pre-trained language model.

Björn Kießwetter, Christoph Lukas, Tim Sieber · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.