Model techniques map
Techniquespost-trainingreward modelling

implementation detail · filed under post-training

Public and hidden verifier pairing

Pairs public verifiers that provide diagnostic feedback with hidden verifiers that evaluate held-out scenarios.

source
1
model
1
lab adopt it
1
strongest
used

How sources treat it

One count per evidence span, weakest treatment to strongest.

used 1

Documented in

Evidence

1 span quoted from the sources, strongest treatment first.

Reward hacking is mitigated by isolating agents from verifiers, pairing public verifiers that offer diagnostic feedback with hidden verifiers that evaluate held-out scenarios, and applying penalty-based rewards under limited submission budgets.

usedunclearin Kimi K3Moonshot AI

Filed alongside

Other methods under post-training :: reward modelling.