FedVPA-GP applies variational preference learning in a federated setting with a mixture prior and orthogonal loss to disentangle user preferences on the HH-RLHF dataset.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Post-training for helpfulness in language-model assistants produces boundary-suppression asymmetry, with over-expansion behaviors harder to locally suppress than other dimensions.
citing papers explorer
-
Federated Variational Preference Alignment with Gumbel-Softmax Prior for Personalized User Preferences
FedVPA-GP applies variational preference learning in a federated setting with a mixture prior and orthogonal loss to disentangle user preferences on the HH-RLHF dataset.
-
Boundary Suppression Asymmetry in Post-trained Assistants: Over-expansion as a Controllability Cost
Post-training for helpfulness in language-model assistants produces boundary-suppression asymmetry, with over-expansion behaviors harder to locally suppress than other dimensions.