conftrace_

multilingual safety

10 papers

Explore in graph

Co-occurring keywords · papers mentioning both

large language model (9) safety alignment (4) safety evaluation (3) content moderation (3) attack success rate (2) harmful content detection (2) safety benchmark (2) red teaming (2) multilingual nlp (2) unsafe response (1)

Papers

LASA: Language-Agnostic Semantic Alignment at the Semantic Bottleneck for LLM Safety ACL 2026 Layer-wise Swapping for Generalizable Multilingual Safety EACL 2026 CultureGuard: Towards Culturally-Aware Dataset and Guard Model for Multilingual Safety Applications IJCNLP 2025 English as Defense Proxy: Mitigating Multilingual Jailbreak via Eliciting English Safety Knowledge EMNLP 2025 MrGuard: A Multilingual Reasoning Guardrail for Universal LLM Safety EMNLP 2025 Multi-lingual Multi-turn Automated Red Teaming for LLMs NAACL 2025 Rainbow-Teaming for the Polish Language: A Reproducibility Study NAACL 2025 X-Guard: Multilingual Guard Agent for Content Moderation ACL 2025 All Languages Matter: On the Multilingual Safety of LLMs ACL 2024 WalledEval: A Comprehensive Safety Evaluation Toolkit for Large Language Models EMNLP 2024