HaloGuard 2.0: An Open-Weights Constitutional Output Guard for Multilingual Response Safety
cs.CL, cs.CR
Submitted: 2026-11-01
Updated: 2026-11-01
Terminology
Sources
- HaloGuard 1.0: An Open Weights Constitutional Classifier for Multilingual AI Safety
- PolyGuard: A Multilingual Safety Moderation Tool for 17 Languages
- Qwen3Guard Technical Report
- Shieldstral
- The Llama 3 Herd of Models
- WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
- ShieldGemma: Generative AI Content Moderation Based on Gemma
- OmniGuard: Unified Omni-Modal Guardrails with Deliberate Reasoning
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teaming
- Constitutional AI: Harmlessness from AI Feedback
- HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusal
- BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset
- PKU-SafeRLHF: Towards Multi-Level Safety Alignment for LLMs with Human Preference
- XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models
- FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
- SALAD-Bench: A Hierarchical and Comprehensive Safety Benchmark for Large Language Models
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