EasyDeepLearn

How do reward models scale with size?

hard

Answer

  • Larger RMs (closer in size to policy) give better preferences: better calibration, less easy-to-exploit gaps.
  • But: too small → doesn't understand nuance; too large → expensive per training step.
  • Modern: RM around 1/3 of policy size (7B RM for 22B policy).
  • Ensemble of RMs improves robustness against hacking.
  • Some frontier labs use LLM-as-judge (whole LLM) instead of scalar-output RM head.
Check yourself — multiple choice
  • No scaling
  • Larger RMs give better preferences / less exploit gaps but expensive; modern RM ≈ 1/3 policy size (7B for 22B); ensembles + LLM-as-judge for robustness against hacking
  • Random
  • Same size always

RM scaling: bigger better; RM ≈ 1/3 policy size; ensembles + LLM-judge.

#llm#alignment

Practise Reinforcement Learning

214 interview questions in this topic.

Related questions