MRM reformulates personalized LLM reward modeling as meta-learning to enable rapid adaptation to new users with limited feedback.
Generative judge for evaluating alignment
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
One Adapts to Any: Meta Reward Modeling for Personalized LLM Alignment
MRM reformulates personalized LLM reward modeling as meta-learning to enable rapid adaptation to new users with limited feedback.