paper-with-me

Papers

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

2023-10-02 · Wenxuan Wang, Zhaopeng Tu, Chang Chen, Youliang Yuan, Jen-tse Huang, Wenxiang Jiao, Michael R. Lyu

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.

📄 PDF Abstract BibTeX arXiv:2310.00905

Code (1)

jarviswang94/multilingual_safety_benchmark 공식 구현

Tasks

AllSafety Alignment

Similar Papers 제목 키워드 기반

Exploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language Models

2026-06-02 · Hashmat Shadab Malik, Muzammal Naseer, Salman Khan arxiv

Multimodal Large Language Models integrate visual perception into language reasoning, introducing a continuous attack surface susceptible to adversarial attacks. Prior work on MLLM robustness has focused largely on Engli…

Adversarial Robustness

LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language Models

2025-08-18 · Zhiyuan Ning, Tianle Gu, Jiaxin Song, Shixin Hong 외 arxiv

The widespread adoption and increasing prominence of large language models (LLMs) in global technologies necessitate a rigorous focus on ensuring their safety across a diverse range of linguistic and cultural contexts. T…

RTP-LX: Can LLMs Evaluate Toxicity in Multilingual Scenarios?

2024-04-22 · Adrian de Wynter, Ishaan Watts, Tua Wongsangaroonsri, Minghui Zhang 외

Large language models (LLMs) and small language models (SLMs) are being adopted at remarkable speed, although their safety still remains a serious concern. With the advent of multilingual S/LLMs, the question now becomes…

Align Once, Benefit Multilingually: Enforcing Multilingual Consistency for LLM Safety Alignment

2026-02-18 · Yuyan Bu, Xiaohao Liu, ZhaoXing Ren, Yaodong Yang 외 arxiv

The widespread deployment of large language models (LLMs) across linguistic communities necessitates reliable multilingual safety alignment. However, recent efforts to extend alignment to other languages often require su…

CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications

2025-08-03 · Raviraj Joshi, Rakesh Paul, Kanishk Singla, Anusha Kamath 외 arxiv

The increasing use of Large Language Models (LLMs) in agentic applications highlights the need for robust safety guard models. While content safety in English is well-studied, non-English languages lack similar advanceme…

Synthetic Data GenerationZero-shot GeneralizationCross-Lingual TransferMachine Translation