Unified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection

TL;DR

This paper introduces a resource-efficient, unified toxicity detection system for gaming communities that leverages soft-prompting and GPT-4o-mini for multi-game and multilingual support, achieving high accuracy with reduced computational costs.

Contribution

It presents a novel soft-prompting method for multi-game toxicity detection and an LLM-assisted label transfer framework for multilingual support, improving scalability and efficiency.

Findings

Achieved macro F1-scores up to 58.88% in multiple languages.

Unified model reduces computational resources compared to separate models.

Successfully identified 50 sanctionable players daily per game.

Abstract

Toxicity detection in gaming communities faces significant scaling challenges when expanding across multiple games and languages, particularly in real-time environments where computational efficiency is crucial. We present two key findings to address these challenges while building upon our previous work on ToxBuster, a BERT-based real-time toxicity detection system. First, we introduce a soft-prompting approach that enables a single model to effectively handle multiple games by incorporating game-context tokens, matching the performance of more complex methods like curriculum learning while offering superior scalability. Second, we develop an LLM-assisted label transfer framework using GPT-4o-mini to extend support to seven additional languages. Evaluations on real game chat data across French, German, Portuguese, and Russian achieve macro F1-scores ranging from 32.96% to 58.88%, with particularly strong performance in German, surpassing the English benchmark of 45.39%. In production, this unified approach significantly reduces computational resources and maintenance overhead compared to maintaining separate models for each game and language combination. At Ubisoft, this model successfully identifies an average of 50 players, per game, per day engaging in sanctionable behavior.