BrainwashedLLM automates RL-based Chain-of-Thought jailbreaks for LRMs
BrainwashedLLM automates discovery of reasoning-based jailbreaks that transfer zero-shot to larger LRMs.
1 stories, newest first · one card per story
BrainwashedLLM automates discovery of reasoning-based jailbreaks that transfer zero-shot to larger LRMs.
Today 1.6K readers · 2.4K views · 771 reads · all time 189K views