HyRe personalizes reward models at test time by reweighting an ensemble of heads trained on aggregate preferences, using few target examples to outperform uniform averaging and prior methods on RewardBench and 32 tasks.
Regularizing hidden states enables learning generalizable reward model for llms
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2024 2verdicts
UNVERDICTED 2representative citing papers
Data-centric filtering yields an 80K preference dataset and reward models that lead RewardBench while boosting other top entries.
citing papers explorer
-
Test-Time Alignment via Hypothesis Reweighting
HyRe personalizes reward models at test time by reweighting an ensemble of heads trained on aggregate preferences, using few target examples to outperform uniform averaging and prior methods on RewardBench and 32 tasks.
-
Skywork-Reward: Bag of Tricks for Reward Modeling in LLMs
Data-centric filtering yields an 80K preference dataset and reward models that lead RewardBench while boosting other top entries.