Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Shifting the Gradient: Understanding How Defensive Training Methods Protect Language Model Integrity
Satchel Grant, Victor Gillioz, Jake Ward +1
Defensive training methods such as positive preventative steering (PPS) and inoculation prompting (IP) offer surprising results through seemingly similar processes: both add trait-…
cs.LG2025
Addressing divergent representations from causal interventions on neural networks
Satchel Grant, Simon Jerome Han, Alexa R. Tartaglini +1
A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to understand what those representations encod…