conftrace_

safety prompt

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

refusal direction (1) harmful queries (1) large language model (1) cross-lingual generalization (1) multilingual language model (1) jailbreak defense (1) representation space (1) soft prompt (1) optimization (1)

Papers

Multilingual Collaborative Defense for Large Language Models EMNLP 2025 On Prompt-Driven Safeguarding for Large Language Models ICML 2024