Summary: Perfectly labeled outcomes in training can still boost reward hacking tendencies in generalization. This can hold even when the train/test sets are drawn from the exact same distribution. We induce this surprising effect via a form of context distillation, which we call re-contextualization:

Generate model completions with a hack-encouraging system prompt + neutral user prompt.
Filter the completions to remove hacks.
Train on these prompt-completion pairs with the system prompt removed.

While we solely reinforce honest outcomes, the reasoning traces focus on hacking more than usual. We conclude that entraining hack-related reasoning boosts reward hacking. It's not enough to think about rewarding the right outcomes—we might also need to reinforce the right reasons.

Introduction

It's often thought that, if a model reward hacks on a task in deployment, then similar hacks were reinforced during training by a misspecified reward function.[1] In METR's report on reward hacking [...]