# In-game Toxic Detection: Bi-directional Representations with Attention Residuals

arXiv: https://arxiv.org/abs/2609.34584 · HTML: https://mlsanity.com/paper/2609.34584/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 10 references that are in the map.
- First posted on arXiv 28 Sep 2026.

## Builds on (most cited first, 5 of 5)

- [Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling](https://mlsanity.com/paper/1609.01454/) (2016)
- [Joint Slot Filling and Intent Detection via Capsule Neural Networks](https://mlsanity.com/paper/1812.09471/) (2018)
- [A Bi-model based RNN Semantic Frame Parsing Model for Intent Detection and Slot Filling](https://mlsanity.com/paper/1812.10235/) (2018)
- [CONDA: a CONtextual Dual-Annotated dataset for in-game toxicity understanding and detection](https://mlsanity.com/paper/2106.06213/) (2021)
- [In-game Toxic Language Detection: Shared Task and Attention Residuals](https://mlsanity.com/paper/2211.05995/) (2022)

## Abstract (arXiv)

In-game toxic language has emerged as a critical concern in the gaming industry and community. While several frameworks and models for online game toxicity analysis have been proposed, detecting toxicity in player chat utterances remains a formidable challenge: stemming not only from the extremely short length of such utterances but also from the heavy reliance on game slang, abbreviations, and domain-specific jargon, which generic language models are poorly suited to recognize. This paper presents a shared task for in-game toxic language detection built upon real-world in-game chat data, and proposes the best-preforming model for the toxic language slot filling: Bi-directional Representations with Attention Residuals (BRAR). Experimental results demonstrate that BRAR effectively captures the global context and outperforms the existing baselines on slot filling.