用轻量提示和大模型迁移，一模型通吃多游戏多语言毒液检测。
Unified Game Moderation: Soft-Prompting and LLM-Assisted Label Transfer for Resource-Efficient Toxicity Detection
- 用游戏上下文软提示让单模型适配多游戏，效果不输复杂方法。
- 用GPT-4o-mini迁移标签，7种新语言平均宏F1达32.96%~58.88%。
- 生产中日均识别50名违规玩家，显著降低资源与维护成本。
游戏社区的毒性检测在跨多游戏、多语言扩展时面临巨大规模挑战，尤其在实时环境中计算效率至关重要。本文基于此前提出的ToxBuster（一种BERT-based实时毒性检测系统），提出两项关键改进：首先，引入软提示方法，通过加入游戏上下文标记，使单一模型有效处理多游戏场景，性能媲美课程学习等复杂方法，且可扩展性更优；其次，设计基于GPT-4o-mini的大模型辅助标签迁移框架，将支持扩展至七种新增语言。在法语、德语、葡萄牙语和俄语的真实游戏聊天数据上评估，宏F1得分范围为32.96%至58.88%，其中德语表现尤为突出，超过英文基准的45.39%。在育碧实际部署中，该统一方案显著降低计算资源与维护开销，相比为每对游戏-语言组合单独维护模型，效率大幅提升。该模型每日可平均识别每款游戏中约50名存在可制裁行为的玩家。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。