Multilingual Safety Alignment via Self-Distillation

• URL: http://arxiv.org/abs/2605.02971v2
• Date: Thu, 07 May 2026 19:25:15 GMT
• Title: Multilingual Safety Alignment via Self-Distillation
• Abstract summary: Large language models (LLMs) exhibit severe multilingual safety misalignment.<n>We propose a cross-lingual safeguard transfer framework named Multilingual Self-Distillation (MSD)<n>Our framework is flexible and can be integrated with different self-distillation strategies.
• Score: 17.94152626632751
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models (LLMs) exhibit severe multilingual safety misalignment: they possess strong safeguards in high-resource languages but remain highly vulnerable to jailbreak attacks in low-resource languages. Current safety alignment methods generally rely on high-quality response data for each target language, which is expensive and difficult to generate. In this paper, we propose a cross-lingual safeguard transfer framework named Multilingual Self-Distillation (MSD). This framework transfers an LLM's inherent safety capabilities from high-resource (e.g., English) to low-resource (e.g., Javanese) languages, overcoming the need for response data in any language. Our framework is flexible and can be integrated with different self-distillation strategies. Specifically, we implement two concrete methods -- on-policy MSD and off-policy MSD -- both of which enable effective cross-lingual safety transfer using only multilingual queries. Furthermore, we propose Dual-Perspective Safety Weighting (DPSW), a divergence measure to optimize the distillation objective. By jointly considering the perspectives of both the teacher and the student, DPSW adaptively increases the penalty weights on safety-critical tokens while reducing the weights on non-critical tokens. Extensive experiments on representative LLMs across diverse multilingual jailbreak and utility benchmarks demonstrate that our method consistently achieves superior multilingual safety performance. Notably, it generalizes effectively to more challenging datasets and unseen languages while preserving the model's general capabilities.

Related papers

• 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)
• Multilingual Refusal Alignment for Safer Large Language Models [53.64286756804503]
  We investigate whether single-language alignment transfers cross-lingually, how language consistency is preserved during training, and the resulting trade-offs with general knowledge capabilities.<n>We introduce RefusEU, a novel refusal alignment dataset covering 12 European languages, including a dedicated test set for evaluating current state-of-the-art models.<n>Our controlled Direct Preference Optimization (DPO) experiments provide two key insights: aligning models exclusively in English is insufficient to ensure cross-lingual safety, even for the same harm categories, whereas training on multilingual datasets can improve safety without degrading general performance, as measured by the Global MMLU benchmark.
  arXiv  Detail & Related papers  (2026-04-24T09:29:14Z)
• 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)
• Layer-wise Swapping for Generalizable Multilingual Safety [8.658596218544773]
  Existing safety datasets are predominantly English centric, limiting progress in multilingual safety alignment.<n>We propose a safety aware layer swapping method that transfers safety alignment from an English safety expert to low resource language experts without additional training.
  arXiv  Detail & Related papers  (2026-01-30T06:22:02Z)
• MPO: Multilingual Safety Alignment via Reward Gap Optimization [88.76638442683391]
  Large language models (LLMs) have become increasingly central to AI applications worldwide.<n>Existing preference learning methods for safety alignment, such as RLHF and DPO, are primarily monolingual and struggle with noisy multilingual data.<n>We introduce Multilingual reward gaP Optimization (MPO), a novel approach that leverages the well-aligned safety capabilities of the dominant language (English) to improve safety alignment across multiple languages.
  arXiv  Detail & Related papers  (2025-05-22T16:24:51Z)
• MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety [56.77103365251923]
  Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking.<n>This vulnerability is exacerbated in multilingual settings, where multilingual safety-aligned data is often limited.<n>We introduce a multilingual guardrail with reasoning for prompt classification.
  arXiv  Detail & Related papers  (2025-04-21T17:15:06Z)
• X-Guard: Multilingual Guard Agent for Content Moderation [8.233872344445675]
  X-Guard is a transparent multilingual safety agent designed to provide content moderation across diverse linguistic contexts.<n>Our approach includes curating and enhancing multiple open-source safety datasets with explicit evaluation rationales.<n>Our empirical evaluations demonstrate X-Guard's effectiveness in detecting unsafe content across multiple languages.
  arXiv  Detail & Related papers  (2025-04-11T01:58:06Z)
• All Languages Matter: On the Multilingual Safety of Large Language Models [96.47607891042523]
  We build the first multilingual safety benchmark for large language models (LLMs) XSafety covers 14 kinds of commonly used safety issues across 10 languages that span several language families. We propose several simple and effective prompting methods to improve the multilingual safety of ChatGPT.
  arXiv  Detail & Related papers  (2023-10-02T05:23:34Z)

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.