XL-SafetyBench: A Country-Grounded Cross-Cultural Benchmark for LLM Safety and Cultural Sensitivity

arXiv:2605.05662 · cs.CL, cs.AI · Submitted 2026-05-07 · Read on arXiv

cs.CL, cs.AI

Submitted: 2026-05-07

Updated: 2026-10-10

Code: https://github.com/QwenLM/Qwen3

Terminology

• Benchmark — 4× in this paper · explained in 2 episodes
• Alignment — 1× in this paper · explained in 1 episode
• Attack Success Rate — 1× in this paper
• Attack Success Rate (ASR) — 1× in this paper · explained in 3 episodes
• Neutral-Safe Rate — 1× in this paper
• Robustness — 1× in this paper · explained in 5 episodes

Sources

• The Multilingual Alignment Prism: Aligning Global and Local Preferences to Reduce Harm
• Towards Measuring and Modeling "Culture" in LLMs: A Survey
• Teuken-7B-Base & Teuken-7B-Instruct: Towards European LLMs
• K2-Think: A Parameter-Efficient Reasoning System
• Multilingual Jailbreak Challenges in Large Language Models
• Towards Measuring the Representation of Subjective Global Opinions in Language Models
• CroissantLLM: A Truly Bilingual French-English Language Model
• Gaperon: A Peppered English-French Generative Language Model Suite
• Salamandra Technical Report
• The Lucie-7B LLM and the Lucie Training Dataset: Open resources for multilingual language generation
• SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
• K-EXAONE Technical Report
• LLM-jp: A Cross-organizational Project for the Research and Development of Fully Open Japanese LLMs
• LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language Models
• PARAM-1 BharatGen 2.9B Model
• RakutenAI-7B: Extending Large Language Models for Japanese
• NormAd: A Framework for Measuring the Cultural Adaptability of Large Language Models
• RigoChat 2: an adapted language model to Spanish using a bounded dataset and reduced hardware
• Jais and Jais-chat: Arabic-Centric Foundation and Instruction-Tuned Open Generative Large Language Models
• Sailor2: Sailing in South-East Asia with Inclusive Multilingual LLMs

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering