# Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons

arXiv: https://arxiv.org/abs/2602.01283 · HTML: https://mlsanity.com/paper/2602.01283/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Feb 2026.

## Built on by (most cited first, 8 of 8)

- [Multilingual Safety Alignment via Self-Distillation](https://mlsanity.com/paper/2605.02971/) (2026)
- [Targeted Interpretable Safety Neuron Enhancement for Multilingual Vision-Language Large Models](https://mlsanity.com/paper/2604.08881/) (2026)
- [Distill Where the Student Goes: Teacher-Regularized RL for English-Evidence Cross-Lingual RAG](https://mlsanity.com/paper/2607.02966/) (2026)
- [One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs](https://mlsanity.com/paper/2607.27917/) (2026)
- [SafeNexus: Discovering and Steering Modality-Universal Safety Neurons in MLLMs](https://mlsanity.com/paper/2607.28969/) (2026)
- [Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways](https://mlsanity.com/paper/2608.09095/) (2026)
- [LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review](https://mlsanity.com/paper/2608.14626/) (2026)
- [When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs](https://mlsanity.com/paper/2608.29936/) (2026)

## Abstract (arXiv)

Multilingual safety remains significantly imbalanced, leaving non-high-resource (NHR) languages vulnerable compared to robust high-resource (HR) ones. Moreover, the neural mechanisms driving safety alignment remain unclear despite observed cross-lingual representation transfer. In this paper, we find that LLMs contain a set of cross-lingual shared safety neurons (SS-Neurons), a remarkably small yet critical neuronal subset that jointly regulates safety behavior across languages. We first identify monolingual safety neurons (MS-Neurons) and validate their causal role in safety refusal behavior through targeted activation and suppression. Our cross-lingual analyses then identify SS-Neurons as the subset of MS-Neurons shared between HR and NHR languages, serving as a bridge to transfer safety capabilities from HR to NHR domains. We observe that suppressing these neurons causes concurrent safety drops across NHR languages, whereas reinforcing them improves cross-lingual defensive consistency. Building on these insights, we propose a simple neuron-oriented training strategy that targets SS-Neurons based on language resource distribution and model architecture. Experiments demonstrate that fine-tuning this tiny neuronal subset outperforms state-of-the-art methods, significantly enhancing NHR safety while maintaining the model's general capabilities. The code and dataset will be available athttps://github.com/1518630367/SS-Neuron-Expansion.