Inoculation Midtraining with Learned Neologisms
Inoculation Midtraining confines unsafe LLM behavior to a neologism-marked context, reducing misalignment after unsafe post-training but leaking under nearby contextual cues.
1 stories, newest first · one card per story
Inoculation Midtraining confines unsafe LLM behavior to a neologism-marked context, reducing misalignment after unsafe post-training but leaking under nearby contextual cues.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views