Who Pays More for Safety? Measuring the Disparate Cost of Safety Alignment across Languages
cs.CL
Submitted: 2026-08-23
Updated: 2026-11-09
Terminology
Sources
- GPT-4 Technical Report
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Constitutional AI: Harmlessness from AI Feedback
- The Llama 3 Herd of Models
- Safety Tax: Safety Alignment Makes Your Large Reasoning Models Less Reasonable
- Analyzing Bias in False Refusal Behavior of Large Language Models for Hate Speech Detoxification
- Is ChatGPT A Good Translator? Yes With GPT-4 As The Engine
- There Is More to Refusal in Large Language Models than a Single Direction
- LinguaSafe: A Comprehensive Multilingual Safety Benchmark for Large Language Models
- Olmo 3
- Qwen2.5 Technical Report
- Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
- OpenAI GPT-5 System Card
- Aya Dataset: An Open-Access Collection for Multilingual Instruction Tuning
- Gemma 3 Technical Report
- Towards Safety and Helpfulness Balanced Responses via Controllable Large Language Models
- Qwen3 Technical Report
- From Hard Refusals to Safe-Completions: Toward Output-Centric Safety Training
- LLMs Encode Harmfulness and Refusal Separately
Related papers
- ALARM: Audio-Language Alignment for Reasoning Models
- ThinkSum: Probabilistic reasoning over sets using large language models
- Coherence boosting: When your pretrained language model is not paying enough attention
- From Facts to Insights: A Persona-Driven Dual Memory Framework and Dataset for Role-Playing Agents
- Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
- The Art of Asking: Multilingual Prompt Optimization for Synthetic Data