When Do Model Internals Help? Exploring the Role of Representation Engineering in LLM Safety
Matched tests find DPO controls LLM safety best, while representation probes monitor cheaply and can repair fine-tuning damage.
1 stories, newest first · one card per story
Matched tests find DPO controls LLM safety best, while representation probes monitor cheaply and can repair fine-tuning damage.
Today 1.5K readers · 2.4K views · 757 reads · all time 189K views