Collaborative Personalized Preference Alignment for LLMs under Data Deficiency
cs.LG
Submitted: 2026-10-05
Updated: 2026-10-05
Terminology
Sources
- Controllable Preference Optimization: Toward Controllable Multi-Objective Alignment
- Personalized Soups: Personalized Large Language Model Alignment via Post-hoc Parameter Merging
- Improving Federated Learning Personalization via Model Agnostic Meta Learning
- Personalized Language Modeling from Personalized Human Feedback
- On First-Order Meta-Learning Algorithms
- FIRM: Federated In-client Regularized Multi-objective Alignment for Large Language Models
- Towards Federated RLHF with Aggregated Client Preference for LLMs
- Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment
- Personalized Federated Fine-Tuning for LLMs via Data-Driven Heterogeneous Model Architectures
- Beyond One-Preference-Fits-All Alignment: Multi-Objective Direct Preference Optimization
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks