HRL/LRL Safety Prompts
Benchmarks
TaskDatasetSOTA resultTrendResults
HRL/LRL Safety Prompts Tamil Multi-Image v1
0ASR
6
HRL/LRL Safety Prompts Welsh Multi-Image v1
0ASR
6
HRL/LRL Safety Prompts English, Single Image v1
0ASR
6
HRL LRL Safety Prompts Tamil Single Image v1
0ASR
6
HRL/LRL Safety Prompts Welsh Single Image v1
6ASR
6
HRL LRL Safety Prompts Tamil Text v1
0Attack Success Rate
6
HRL/LRL Safety Prompts Welsh Text v1
0Attack Success Rate
6