All Languages Matter: On the Multilingual Safety of Large Language Models

• URL: http://arxiv.org/abs/2310.00905v2
• Date: Thu, 20 Jun 2024 14:15:23 GMT
• Title: All Languages Matter: On the Multilingual Safety of Large Language Models
• Abstract summary: 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.
• Score: 96.47607891042523
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Safety lies at the core of developing and deploying large language models (LLMs). However, previous safety benchmarks only concern the safety in one language, e.g. the majority language in the pretraining data such as English. In this work, we build the first multilingual safety benchmark for LLMs, XSafety, in response to the global deployment of LLMs in practice. XSafety covers 14 kinds of commonly used safety issues across 10 languages that span several language families. We utilize XSafety to empirically study the multilingual safety for 4 widely-used LLMs, including both close-API and open-source models. Experimental results show that all LLMs produce significantly more unsafe responses for non-English queries than English ones, indicating the necessity of developing safety alignment for non-English languages. In addition, we propose several simple and effective prompting methods to improve the multilingual safety of ChatGPT by evoking safety knowledge and improving cross-lingual generalization of safety alignment. Our prompting method can significantly reduce the ratio of unsafe responses from 19.1% to 9.7% for non-English queries. We release our data at https://github.com/Jarviswang94/Multilingual_safety_benchmark.

Related papers

• 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)
• IndicSafe: A Benchmark for Evaluating Multilingual LLM Safety in South Asia [0.6978180153516672]
  We present the first systematic evaluation of large language models (LLMs) safety across 12 Indic languages.<n>Cross-language agreement is just 12.8%, and textttSAFE rate variance exceeds 17% across languages.<n>We release textscIndicSafe, the first benchmark to enable culturally informed safety evaluation for Indic deployments.
  arXiv  Detail & Related papers  (2026-03-18T16:54:07Z)
• 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)
• LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language Models [22.273388934888278]
  Our dataset comprises 45k entries in 12 languages, ranging from Hungarian to Malay.<n>Our benchmark provides a comprehensive suite of metrics for in-depth safety evaluation.
  arXiv  Detail & Related papers  (2025-08-18T08:59:01Z)
• Beyond Weaponization: NLP Security for Medium and Lower-Resourced Languages in Their Own Right [0.0]
  This work examines the security of LMs for lower- and medium-resourced languages.<n>We extend existing adversarial attacks for up to 70 languages to evaluate the security of monolingual and multilingual LMs for these languages.
  arXiv  Detail & Related papers  (2025-07-04T10:54:04Z)
• 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)
• MR. Guard: Multilingual Reasoning Guardrail using Curriculum Learning [56.79292318645454]
  Large Language Models (LLMs) are susceptible to adversarial attacks such as jailbreaking. This vulnerability is exacerbated in multilingual setting, where multilingual safety-aligned data are often limited. We propose an approach to build a multilingual guardrail with reasoning.
  arXiv  Detail & Related papers  (2025-04-21T17:15:06Z)
• PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages [27.318299273902984]
  PolyGUARD is a new state-of-the-art multilingual safety model for safeguarding Large Language Models (LLMs) generations. It is trained on the largest multilingual safety training corpus to date containing 1.91M samples across 17 languages. PolyGUARDPROMPTS is a high quality multilingual benchmark with 29K samples for the evaluation of safety guardrails.
  arXiv  Detail & Related papers  (2025-04-06T06:09:21Z)
• LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps [63.10843814055688]
  M-ALERT is a benchmark that evaluates the safety of Large Language Models in five languages: English, French, German, Italian, and Spanish. M-ALERT includes 15k high-quality prompts per language, totaling 75k, following the detailed ALERT taxonomy.
  arXiv  Detail & Related papers  (2024-12-19T16:46:54Z)
• Benchmarking LLM Guardrails in Handling Multilingual Toxicity [57.296161186129545]
  We introduce a comprehensive multilingual test suite, spanning seven datasets and over ten languages, to benchmark the performance of state-of-the-art guardrails. We investigate the resilience of guardrails against recent jailbreaking techniques, and assess the impact of in-context safety policies and language resource availability on guardrails' performance. Our findings show that existing guardrails are still ineffective at handling multilingual toxicity and lack robustness against jailbreaking prompts.
  arXiv  Detail & Related papers  (2024-10-29T15:51:24Z)
• Towards Understanding the Fragility of Multilingual LLMs against Fine-Tuning Attacks [18.208272960774337]
  Large Language Models (LLMs) have sparked widespread concerns about their safety. Recent work demonstrates that safety alignment of LLMs can be easily removed by fine-tuning. We take a further step to understand fine-tuning attacks in multilingual LLMs.
  arXiv  Detail & Related papers  (2024-10-23T18:27:36Z)
• Mix Data or Merge Models? Optimizing for Diverse Multi-Task Learning [13.99794032197004]
  Large Language Models (LLMs) have been adopted and deployed worldwide for a broad variety of applications. We explore model merging in a diverse multi-task setting, combining safety and general-purpose tasks within a multilingual context. We find that objective-based merging is more effective than mixing data, with improvements of up to 8% and 10% in general performance and safety respectively.
  arXiv  Detail & Related papers  (2024-10-14T17:58:01Z)
• CoSafe: Evaluating Large Language Model Safety in Multi-Turn Dialogue Coreference [29.55937864144965]
  This study is the first to study safety in multi-turn dialogue coreference in large language models (LLMs) We created a dataset of 1,400 questions across 14 categories, each featuring multi-turn coreference safety attacks. The highest attack success rate was 56% with the LLaMA2-Chat-7b model, while the lowest was 13.9% with the Mistral-7B-Instruct model.
  arXiv  Detail & Related papers  (2024-06-25T15:13:02Z)
• ALERT: A Comprehensive Benchmark for Assessing Large Language Models' Safety through Red Teaming [64.86326523181553]
  ALERT is a large-scale benchmark to assess safety based on a novel fine-grained risk taxonomy. It aims to identify vulnerabilities, inform improvements, and enhance the overall safety of the language models.
  arXiv  Detail & Related papers  (2024-04-06T15:01:47Z)
• Multilingual Jailbreak Challenges in Large Language Models [96.74878032417054]
  In this study, we reveal the presence of multilingual jailbreak challenges within large language models (LLMs) We consider two potential risky scenarios: unintentional and intentional. We propose a novel textscSelf-Defense framework that automatically generates multilingual training data for safety fine-tuning.
  arXiv  Detail & Related papers  (2023-10-10T09:44:06Z)
• Low-Resource Languages Jailbreak GPT-4 [19.97929171158234]
  Our work exposes the inherent cross-lingual vulnerability of AI safety training and red-teaming of large language models (LLMs) On the AdvBenchmark, GPT-4 engages with the unsafe translated inputs and provides actionable items that can get the users towards their harmful goals 79% of the time. Other high-/mid-resource languages have significantly lower attack success rate, which suggests that the cross-lingual vulnerability mainly applies to low-resource languages.
  arXiv  Detail & Related papers  (2023-10-03T21:30:56Z)
• SafetyBench: Evaluating the Safety of Large Language Models [54.878612385780805]
  SafetyBench is a comprehensive benchmark for evaluating the safety of Large Language Models (LLMs) It comprises 11,435 diverse multiple choice questions spanning across 7 distinct categories of safety concerns. Our tests over 25 popular Chinese and English LLMs in both zero-shot and few-shot settings reveal a substantial performance advantage for GPT-4 over its counterparts.
  arXiv  Detail & Related papers  (2023-09-13T15:56:50Z)
• Safety Assessment of Chinese Large Language Models [51.83369778259149]
  Large language models (LLMs) may generate insulting and discriminatory content, reflect incorrect social values, and may be used for malicious purposes. To promote the deployment of safe, responsible, and ethical AI, we release SafetyPrompts including 100k augmented prompts and responses by LLMs.
  arXiv  Detail & Related papers  (2023-04-20T16:27:35Z)

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.