Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Toxicity Mitigation on Specialized category Manually-designed jailbreak attacks

4.5RTR

Optimus (CH)

2.34816.87431.445.926Jul 8, 2025
Updated 16d ago

Evaluation Results

MethodLinks
2025.07
4.55.859.9-
2025.07
13.15.469.7-
2025.07
58.36.019.73.21