specific method · filed under post-training
Principle-conditioned Generative Reward Model
A generative reward model described as following principles; the evidence does not specify the principles or conditioning procedure.
Also called principle-following GenRM.
- 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.
A principle-following GenRM makes this process much more flexible
usedunclearin Nemotron 3 Ultra (Chat teacher)NVIDIA
Filed alongside
Other methods under post-training :: reward modelling.
Generative Reward ModelGroupwise Agentic GradingGroupwise Reward SynthesisAdversarial screeningLength-adjusted RL rewardVerifier cross-checkingAbstention-aware reward for factual QAAgentic Generative Reward ModelBehavior rubricsBinary task verifierBinary terminal-verifier rewardCollaboration bonusDeterministic chain of checkersDirect RL optimization of a generative reward modelFive-dimension comparative grading of passing patchesHack-agent screeningHybrid reward systemLanguage consistency rewardMonitoring-only penalty strategyMulti-level reward formulationMultiplicative reward synthesisNegative checks for unintended side effectsOutcome Reward ModelPer-token tool-error reward shaping