conftrace_

code-switching attack

1 paper

Explore in graph

Co-occurring keywords · papers mentioning both

guardrail system (1) large language model (1) multilingual safety (1) reward optimization (1) safety evaluation (1) language model (1) adversarial defense (1) content moderation (1) multilingual nlp (1)

Papers

X-Guard: Multilingual Guard Agent for Content Moderation ACL 2025