User Model Extraction via Belief Self-Distillation
Belief Self-Distillation reads and rewrites an LLM's user beliefs, changing refusals with the request fixed.
1 stories, newest first · one card per story
Belief Self-Distillation reads and rewrites an LLM's user beliefs, changing refusals with the request fixed.
Today 1.6K readers · 2.5K views · 779 reads · all time 189K views