Fighting the COVID-19 Infodemic with a Holistic BERT Ensemble
Giorgos Tziafas, Konstantinos Kogkalidis, Tommaso Caselli
Abstract
This paper describes the TOKOFOU system, an ensemble model for misinformation detection tasks based on six different transformer-based pre-trained encoders, implemented in the context of the COVID-19 Infodemic Shared Task for English. We fine tune each model on each of the task's questions and aggregate their prediction scores using a majority voting approach. TOKOFOU obtains an overall F1 score of 89.7%, ranking first.
Results
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Misinformation | NLP4IF-2021--Fighting the COVID-19 Infodemic | Average F1 | 89.7 | TOKOFOU |
Related Papers
SHIELD: A Secure and Highly Enhanced Integrated Learning for Robust Deepfake Detection against Adversarial Attacks2025-07-17Leveraging Pre-Trained Visual Models for AI-Generated Video Detection2025-07-17KEN: Knowledge Augmentation and Emotion Guidance Network for Multimodal Fake News Detection2025-07-13LLM-Stackelberg Games: Conjectural Reasoning Equilibria and Their Applications to Spearphishing2025-07-12Multi-Agent Retrieval-Augmented Framework for Evidence-Based Counterspeech Against Health Misinformation2025-07-09LLMs are Introvert2025-07-08Remember Past, Anticipate Future: Learning Continual Multimodal Misinformation Detectors2025-07-08The Ethical Implications of AI in Creative Industries: A Focus on AI-Generated Art2025-07-08