Why Do Safety Guardrails Degrade Across Languages?

• URL: http://arxiv.org/abs/2605.17173v1
• Date: Sat, 16 May 2026 22:08:54 GMT
• Title: Why Do Safety Guardrails Degrade Across Languages?
• Abstract summary: Large language models exhibit safety degradation in non-English languages.<n>We introduce a latent variable model, a Multi-Group Item Response Theory (IRT) framework, that decouples safety-driving factors.<n>We evaluate the safety robustness of 61 model configurations across 5 closed-model families and 10 languages of varying resource.
• Score: 21.521293656854183
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large language models exhibit safety degradation in non-English languages. Standard evaluation relies on Jailbreak Success Rate (JSR), which confounds several safety-driving factors into one, obscuring the specific cause(s) of safety failure. We introduce a latent variable model, a Multi-Group Item Response Theory (IRT) framework, that decouples safety-driving factors such as language-agnostic safety robustness ($θ$), intrinsic prompt hardness ($β$), global language processing difficulty ($γ$), and a prompt-specific cross-lingual safety gap ($τ$). Using the MultiJail dataset, we evaluate the safety robustness of 61 model configurations across 5 closed-model families and 10 languages of varying resource, aggregating a dataset of 1.9 million rows. Exploratory Factor Analysis shows safety is primarily unidimensional: models refuse different harm types mainly through a shared mechanism. Contrary to the expected trend that safety degrades largely in low-resource languages, 22 model configurations are more vulnerable in English than in low-resource languages. Low-resource languages produce more uncertain responses (high entropy) than high-resource languages. Also, high-$τ$ prompts cluster in physical harm categories like Theft and Weapons and lower-resource languages, trends validated through cross-dataset generalization. While global translation quality shows low correlation with $τ$, severe mistranslations drive high-bias outliers, as validated by native speakers. Cultural and conceptual grounding mismatches also contribute to $τ$. In predictive validation, the IRT framework achieves $\mathrm{AUC} = 0.940$, outperforming simpler baselines in predicting safe refusal of unsafe prompts. Our framework reveals concept-language vulnerabilities that aggregate metrics obscure, enabling fairer cross-lingual safety evaluation and targeted improvements in dataset construction.

Related papers

• IndicSafeEval: Safety Robustness of Large Language Models under Multilingual Persuasive Jailbreak Attacks [33.08360320836576]
  We introduce IndicSafeEval, a persuasion-based jailbreak evaluation framework for Indian languages.<n>Our benchmark combines ten safety critical content categories with six human-like persuasive strategies across four different Indian languages.<n>Our analysis shows that the model does not behave equally safely across all languages and prompt styles.
  arXiv  Detail & Related papers  (2026-09-03T12:54:44Z)
• The Illusion of Cross-Lingual Safety in Low-Resource Languages [7.471112976694495]
  Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings.<n>We investigate cross-lingual safety transfer in four African languages, Twi, Hausa, Amharic, and Swahili, using LoDNA, a new safety dataset that pairs literal translations with culturally localized prompts.<n>Our experimental results show that cross-lingual safety transfer is severely limited; harmful prompts retain less than 10% of the English refusal signal across most language-model pairs.
  arXiv  Detail & Related papers  (2026-08-11T17:05:26Z)
• LLM Safety Alignment in Low-Resource Languages: A Systematic Literature Review [9.895109697164283]
  Large Language Models (LLMs) have achieved substantial progress in safety alignment.<n>Their safety guarantees remain significantly weaker in low-resource and multilingual settings.
  arXiv  Detail & Related papers  (2026-07-20T21:11:00Z)
• Schützen: Evaluating LLM Safety in Bulgarian and German Contexts [53.865251738592605]
  This paper introduces Schtzen: a German--Bulgarian safety dataset designed to assess model answerability under risk.<n> Experiments with multilingual and language-specific LLMs reveal pronounced cross-language differences in safety behavior.
  arXiv  Detail & Related papers  (2026-06-09T18:01:19Z)
• Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models [3.2555924024638667]
  Safety-aligned large language models often exhibit sycophancy, which is the tendency to affirm users' opinions regardless of factual accuracy.<n>We present the first large-scale, multi-model evaluation of cross-lingual sycophancy, benchmarking textbfsix instruction-tuned models across textbf38 languages and textbf33 topic categories.
  arXiv  Detail & Related papers  (2026-06-07T04:50:40Z)
• Multilingual Safety Alignment via Self-Distillation [17.94152626632751]
  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.
  arXiv  Detail & Related papers  (2026-05-03T14:22:49Z)
• 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)
• LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety [88.98698230989186]
  Large language models (LLMs) often demonstrate strong safety performance in high-resource languages, yet exhibit severe vulnerabilities in low-resource languages.<n>We attribute this gap to a mismatch between language-agnostic semantic understanding ability and language-dominant safety alignment biased toward high-resource languages.<n>We propose Language-Agnostic Semantic Alignment (LASA), which anchors safety alignment directly in semantic bottlenecks.
  arXiv  Detail & Related papers  (2026-04-13T15:59:50Z)
• Lingua-SafetyBench: A Benchmark for Safety Evaluation of Multilingual Vision-Language Models [54.10540442330978]
  Existing benchmarks are typically multilingual but text-only, or multimodal but monolingual.<n>Recent multilingual red-teaming efforts render harmful prompts into images, yet rely heavily on typography-style visuals.<n>We introduce a benchmark of 100,440 harmful image-text pairs across 10 languages, explicitly partitioned into image-dominant and text-dominant subsets.
  arXiv  Detail & Related papers  (2026-01-30T09:18:13Z)
• RabakBench: Scaling Human Annotations to Construct Localized Multilingual Safety Benchmarks for Low-Resource Languages [3.7678366606419345]
  RabakBench is a new multilingual safety benchmark localized to Singapore's unique linguistic context.<n>The benchmark dataset, including the human-verified translations, and evaluation code are publicly available.
  arXiv  Detail & Related papers  (2025-07-08T13:37:25Z)
• 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)
• 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.