Alex Cloud
Titles as the sources gave them. In 1 entry, with 0 checked quotations.
In the Base
Every entry they appear in.
Gradient Routing Localizes and Removes Unintended Behaviors in RL
According to the post's opening summary, a MATS research team proposes GRAFT, a training method that confines the updates from detected reward hacks to a set of parameters later removed. The authors report it prevents hacks, including ones monitors miss, in experiments limited to small models and simple monitors.