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

arXiv: https://arxiv.org/abs/2506.06347 · HTML: https://mlsanity.com/paper/2506.06347/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 60 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)](https://mlsanity.com/paper/1903.08983/) (2019)
- [On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning](https://mlsanity.com/paper/2212.08061/) (2022)
- [A New Generation of Perspective API: Efficient Multilingual Character-level Transformers](https://mlsanity.com/paper/2202.11176/) (2022)
- [Directions in Abusive Language Training Data: Garbage In, Garbage Out](https://mlsanity.com/paper/2004.01670/) (2020)
- [COLD: A Benchmark for Chinese Offensive Language Detection](https://mlsanity.com/paper/2201.06025/) (2022)
- [Challenges for Toxic Comment Classification: An In-Depth Error Analysis](https://mlsanity.com/paper/1809.07572/) (2018)
- [Facilitating Fine-grained Detection of Chinese Toxic Language: Hierarchical Taxonomy, Resources, and Benchmarks](https://mlsanity.com/paper/2305.04446/) (2023)
- [Toxic Language Detection in Social Media for Brazilian Portuguese: New Dataset and Multilingual Analysis](https://mlsanity.com/paper/2010.04543/) (2020)
- [SWSR: A Chinese Dataset and Lexicon for Online Sexism Detection](https://mlsanity.com/paper/2108.03070/) (2021)
- [Open, Closed, or Small Language Models for Text Classification?](https://mlsanity.com/paper/2308.10092/) (2023)
- [Anyone Can Become a Troll: Causes of Trolling Behavior in Online Discussions](https://mlsanity.com/paper/1702.01119/) (2017)
- [Can LLMs Recognize Toxicity? A Structured Investigation Framework and Toxicity Metric](https://mlsanity.com/paper/2402.06900/) (2024)
- [Efficient Toxic Content Detection by Bootstrapping and Distilling Large Language Models](https://mlsanity.com/paper/2312.08303/) (2023)
- [Improving Adversarial Data Collection by Supporting Annotators: Lessons from GAHD, a German Hate Speech Dataset](https://mlsanity.com/paper/2403.19559/) (2024)
- [Toxicity Detection is NOT all you Need: Measuring the Gaps to Supporting Volunteer Content Moderators](https://mlsanity.com/paper/2311.07879/) (2023)
- [Learning a Better Initialization for Soft Prompts via Meta-Learning](https://mlsanity.com/paper/2205.12471/) (2022)
- [Multi3Hate: Multimodal, Multilingual, and Multicultural Hate Speech Detection with Vision-Language Models](https://mlsanity.com/paper/2411.03888/) (2024)
- [Towards Detecting Contextual Real-Time Toxicity for In-Game Chat](https://mlsanity.com/paper/2310.18330/) (2023)

## Built on by (most cited first, 5 of 5)

- [When to Invoke: Refining LLM Fairness with Toxicity Assessment](https://mlsanity.com/paper/2601.09250/) (2026)
- [Prosocial Behavior Detection in Player Game Chat: From Aligning Human-AI Definitions to Efficient Annotation at Scale](https://mlsanity.com/paper/2508.05938/) (2025)
- [Analyzing Bias in False Refusal Behavior of Large Language Models for Hate Speech Detoxification](https://mlsanity.com/paper/2601.08668/) (2026)
- [Toxicity in Twitch Chats: An LLM-Based Analysis Across Gaming Communities](https://mlsanity.com/paper/2605.24000/) (2026)
- [Language-Specific Gaps in AI Safety Training Datasets](https://mlsanity.com/paper/2608.13695/) (2026)

## Abstract (arXiv)

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.