Work

syuhhh@EEUCA 2026: A Three-Stage Progressive Training Framework for Fine-Grained Toxicity Detection in Online Gaming Communities

Year: 2026

Type: conference-paper

Abstract: This paper presents our 1st-place system for the Shared Task on Fine-Grained Toxicity Detection in Online Gaming (GameTox) at the 9th EEUCA Workshop, co-located with ACL 2026.The task targets 6-class fine-grained toxic intent classification on the official Ga-meTox dataset, comprising 53,000 real-world World of Tanks chat utterances.We propose a three-stage progressive training framework built on XLM-RoBERTa-large: (1) gaming domain adaptive MLM pre-training, (2) multilingual toxicity transfer fine-tuning, and (3) supervised contrastive learning (SCL)-enhanced target task tuning.We further incorporate LLMdriven data augmentation and long-tailed class synthesis.Our system achieves a Macro F1 of 0.7041, ranking 1st among 35 teams.Ablation studies validate each module's contribution, and we release our code to facilitate follow-up research.

Source: Workshop on Event Extraction and Understanding: Challenges and Applications (EEUCA)

DOI: 10.18653/v1/2026.eeuca-1.17

Authors: Yuhao Shi, Yu Wang, Shengjie Zhao

Institution: Tongji University

Language: English

Topic: Hate Speech and Cyberbullying Detection

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Natural Science Foundation of China

Awards: G2484487752, G4606321376, G769818826