Tag
This paper presents RAKSHAK, a multi-task DeBERTa-v3 framework with rationale distillation and Jigsaw-augmented training for classifying toxic intent in World of Tanks chat utterances, achieving 7th place in the GameTox shared task at EEUCA 2026.
This paper presents a hybrid approach for detecting online polarization in English and Hausa using DeBERTa for English and AfroXLMR-Social for Hausa and fine-grained subtasks, with LoRA and data augmentation to address computational and data constraints.
University of Minnesota Duluth team used DeBERTa-V3-base augmented with synthetic data from Gemini 3 and Claude Sonnet 4.5 to classify political question evasions, achieving 8th place at SemEval-2026 Task 6.