Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways

• URL: http://arxiv.org/abs/2608.09095v1
• Date: Mon, 10 Aug 2026 03:48:47 GMT
• Title: Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways
• Abstract summary: We identify and target the cross-layer functional pathways formed during safety signal propagation.<n>We propose a pathways-targeted alignment method based on the cross-lingual shared safety pathways.<n> Experimental results show that updating only a small fraction of pathway parameters significantly improves safety in NHR languages.
• Score: 44.23839982612062
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Uncovering the internal mechanisms underlying the safety capabilities of large language models (LLMs) is crucial for developing trustworthy artificial intelligence. Currently, mechanistic interpretability studies on multilingual safety are largely confined to local components, such as isolated neurons. However, this static and fragmented perspective overlooks the synergy among components and fails to elucidate how safety signals dynamically propagate within the model to drive safety decisions ultimately. In this work, we move beyond isolated neurons to identify and target the cross-layer functional pathways formed during safety signal propagation, thereby uncovering the mechanisms driving the cross-lingual safety gap. Specifically, we first identify monolingual safety pathways and validate their impact on refusing harmful requests. Subsequent cross-lingual analyses reveal a sparse subset of cross-lingual shared safety pathways, confirming that this intersection acts as the internal bridge transferring safety capabilities from high-resource (HR) languages to non-high-resource (NHR) languages. Building on these mechanistic findings, we propose a pathways-targeted alignment method based on the cross-lingual shared safety pathways. Experimental results show that updating only a small fraction of pathway parameters significantly improves safety in NHR languages while largely preserving the model's general capabilities.

Related papers

• Transfer Safety Awareness for Cross-Modal Safety Drift in Multimodal Large Language Models [11.458228829093152]
  We term this cross-modal safety drift and our pilot studies show that the safety response rate for such requests is substantially lower than that for requests containing explicitly unsafe text.<n>We propose safety-awareness representation transfer (SRT), a lightweight direction-refinement method that mitigates cross-modal safety drift with a frozen MLLM backbone.
  arXiv  Detail & Related papers  (2026-09-02T04:12:35Z)
• When Safety Speaks a Language: A Mechanistic Analysis of Safety-Language Identity Entanglement in LLMs [4.92475688183711]
  Safety-relevant features are architecture-dependent in terms of where they are located and how they are distributed across layers.<n>This safety-language entanglement has direct consequences such that ablating safety features impacts not only harmful response rates but also target language.<n>Our findings qualify the language-universality of safety alignment as architecture-dependent and offer a mechanistic account of multilingual safety interventions.
  arXiv  Detail & Related papers  (2026-08-30T18:07:26Z)
• One Anchor for All: Unified Multilingual and Multimodal Safety Alignment for LVLMs [63.29484454957031]
  We propose a neuron-level cross-dimensional safety alignment framework driven by modality- and language-shared safety neurons (MLS-Neurons)<n>Our method significantly outperforms state-of-the-art approaches across diverse multilingual and multimodal safety benchmarks.
  arXiv  Detail & Related papers  (2026-07-30T09:30:03Z)
• Safety Targeted Embedding Exploit via Refinement [1.384477926572109]
  We show that safety mechanisms aligned primarily on English cannot be assumed to generalize across multilingual inputs.<n>We introduce STEER, a gradient-guided attack that translates words into low-resource languages to suppress refusal while preserving harmful intent.<n>We argue that improving multilingual safety requires broader coverage during alignment and mechanisms that explicitly detect and abstain on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2026-07-02T08:17:57Z)
• Do Models Share Safety Representations? Cross-Model Steering for Safe Visual Generation [52.122731171289665]
  We introduce the first framework for cross-model safety steering.<n>Our pipeline never accesses unsafe data on the target side.<n>We evaluate our approach in text-to-image and text-to-video generation across diverse source-target model pairs.
  arXiv  Detail & Related papers  (2026-06-03T18:00:04Z)
• Precise Shield: Explaining and Aligning VLLM Safety via Neuron-Level Guidance [64.18179414483966]
  In real-world deployments, Vision-Language Large Models (VLLMs) face critical challenges from multilingual and multimodal composite attacks.<n>We propose Precise Shield, a two-stage framework that first identifies safety neurons by contrasting activation patterns between harmful and benign inputs.<n>This strategy substantially improves safety while preserving multilingual and multimodal generalization.
  arXiv  Detail & Related papers  (2026-04-10T02:42:52Z)
• Who Transfers Safety? Identifying and Targeting Cross-Lingual Shared Safety Neurons [49.772147495578736]
  Cross-lingual shared safety neurons (SS-Neurons) regulate safety behavior across languages.<n>We propose a neuron-oriented training strategy that targets SS-Neurons based on language resource distribution and model architecture.
  arXiv  Detail & Related papers  (2026-02-01T15:28:02Z)
• Safe-SAIL: Towards a Fine-grained Safety Landscape of Large Language Models via Sparse Autoencoder Interpretation Framework [31.278770676774325]
  We propose Safe-SAIL, a framework for interpreting SAE features within large language models (LLMs)<n>Our approach systematically identifies SAE with best concept-specific interpretability, explains safety-related neurons, and introduces efficient strategies to scale up the interpretation process.
  arXiv  Detail & Related papers  (2025-09-11T11:22:43Z)
• Refusal Direction is Universal Across Safety-Aligned Languages [66.64709923081745]
  In this paper, we investigate the refusal behavior in large language models (LLMs) across 14 languages using PolyRefuse.<n>We uncover the surprising cross-lingual universality of the refusal direction: a vector extracted from English can bypass refusals in other languages with near-perfect effectiveness.<n>We attribute this transferability to the parallelism of refusal vectors across languages in the embedding space and identify the underlying mechanism behind cross-lingual jailbreaks.
  arXiv  Detail & Related papers  (2025-05-22T21:54:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.