# GloSS over Toxicity: Understanding and Mitigating Toxicity in LLMs via Global Toxic Subspace

arXiv: https://arxiv.org/abs/2505.17078 · HTML: https://mlsanity.com/paper/2505.17078/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 May 2025.

## Built on by (most cited first, 4 of 4)

- [Large Language Model Sourcing: A Survey](https://mlsanity.com/paper/2510.10161/) (2025)
- [Circular Reasoning: Understanding Self-Reinforcing Loops in Large Reasoning Models](https://mlsanity.com/paper/2601.05693/) (2026)
- [XGUARD: A Graded Benchmark for Evaluating Safety Failures of Large Language Models on Extremist Content](https://mlsanity.com/paper/2506.00973/) (2025)
- [A Survey of Toxicity Detection and Mitigation Strategies for Multilingual Language Models](https://mlsanity.com/paper/2606.25380/) (2026)

## Abstract (arXiv)

This paper investigates the underlying mechanisms of toxicity generation in Large Language Models (LLMs) and proposes an effective detoxification approach. Prior work typically considers the Feed-Forward Network (FFN) as the main source of toxicity, representing toxic regions as a set of toxic vectors or layer-wise subspaces. However, our in-depth analysis reveals that the global toxic subspace offers a more effective and comprehensive representation of toxic region within the model. Building on this insight, we propose GloSS (Global Toxic Subspace Suppression), a lightweight, four-stage method that mitigates toxicity by identifying and removing the global toxic subspace from the parameters of FFN. Experiments across a range of LLMs show that GloSS achieves state-of-the-art detoxification performance while preserving the models general capabilities, without requiring large-scale data or model retraining.