A dataset revealing high inter-designer disagreement on UI preferences motivates a sample-efficient method that personalizes generative interfaces by embedding new users in the space of prior designers, outperforming baselines in both modeling and user preference.
Personalizing reinforcement learning from human feedback with variational preference learning
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 5roles
background 1polarities
support 1representative citing papers
Equation-to-Behavior Prompting lets large LLMs match cognitive models like Bayesian updating in persuasion games; RL training cuts small-model belief error by 26.5% and improves diverse training outcomes by 2.5-12%.
PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.
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.
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.
citing papers explorer
-
Efficient Personalization of Generative User Interfaces
A dataset revealing high inter-designer disagreement on UI preferences motivates a sample-efficient method that personalizes generative interfaces by embedding new users in the space of prior designers, outperforming baselines in both modeling and user preference.
-
Using Cognitive Models to Improve Language Model Simulation of Human Persuasion Games
Equation-to-Behavior Prompting lets large LLMs match cognitive models like Bayesian updating in persuasion games; RL training cuts small-model belief error by 26.5% and improves diverse training outcomes by 2.5-12%.
-
Beyond Isolated Behaviors: Hierarchical User Modeling for LLM Personalization
PHF applies Bourdieu's Theory of Practice to create hierarchical user models for LLM personalization and reports consistent gains on the LaMP benchmark.
-
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.
-
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.