Get Started
Topic · 3 recaps
Google DeepMind
Play all
...
Posts
Questions
Questions researchers are working on
Follow a question through Rcap’s explanations and the latest papers addressing it.
Search
How should LLM safety be assessed when jailbreak vulnerability varies by language and persuasive phrasing?
English-only tests can overlook safety failures that emerge when harmful requests are expressed in other languages or phrased persuasively. Vulnerability can also differ by harmful-content category, so overall safety scores may conceal specific weaknesses.
Home
Topics
Search
Library