On Llama-3 and Qwen-2.5, removing safety guardrails sharply raises compliance with dangerous bio, chem, and cyber requests, and the resulting safety gap grows with model scale.
Claude 3.5 Haiku
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.CY 1years
2025 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
The Safety Gap Toolkit: Evaluating Hidden Dangers of Open-Source Models
On Llama-3 and Qwen-2.5, removing safety guardrails sharply raises compliance with dangerous bio, chem, and cyber requests, and the resulting safety gap grows with model scale.