PSK@EEUCA 2026: Fine-Tuning Large Language Models with Synthetic Data Augmentation for Multi-Class Toxicity Detection in Gaming Chat
On the map: Synthetic data and self-improvement for LLMs → LLM synthetic data generation
Abstract (arXiv)
This paper describes our system for the EEUCA 2026 Shared Task on Understanding Toxic Behavior in Gaming Communities. The task involves classifying World of Tanks chat messages into six toxicity categories: Non-toxic, Insults/Flaming, Other Offensive, Hate/Harassment, Threats, and Extremism. We explore multiple approaches including encoder-based models, instruction-tuned LLMs with LoRA fine-tuning, hierarchical classification, one-vs-rest strategies, and various ensemble methods. Our best system combines Llama 3.1 8B with carefully calibrated 5% synthetic data augmentation, achieving an F1-macro score of 0.6234 on the test set, placing 4th out of 35 participating teams. We provide extensive analysis of the dataset's annotation patterns and their impact on model generalization, revealing a critical ''validation trap'' phenomenon where high validation performance correlates with poor test transfer.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in LLM synthetic data generation, one of 13 directions in Synthetic data and self-improvement for LLMs. Builds on 6 of its 17 references that are in the map. First posted on arXiv 8 May 2026.
Builds on
6 of 17 references.
References · 6
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2024The Llama 3 Herd of Modelscited by 14,192
- 2019RoBERTa: A Robustly Optimized BERT Pretraining Approachcited by 13,266
- 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
- 2023QLoRA: Efficient Finetuning of Quantized LLMscited by 3,355
- 2015Exploring Cyberbullying and Other Toxic Behavior in Team Competition Online Gamescited by 10
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2025Efficient Toxicity Detection in Gaming Chats: A Comparative Study of Embeddings, Fine-Tuned Transformers and LLMs
- 2025Something Just Like TRuST : Toxicity Recognition of Span and Target
- 2025Rethinking Toxicity Evaluation in Large Language Models: A Multi-Label Perspective
- 2025SMARTER: A Data-efficient Framework to Improve Toxicity Detection with Explanation via Self-augmenting Large Language Models
- 2025<think> So let's replace this phrase with insult... </think> Lessons learned from generation of toxic texts with LLMs
- 2026ToxiTwitch: Toward Emote-Aware Hybrid Moderation for Live Streaming Platforms
- 2026A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models
- 2025Optimus: A Robust Defense Framework for Mitigating Toxicity while Fine-Tuning Conversational AI