Personalized Federated Direct Preference Optimization via LoRA Adapters

arXiv:2610.12885 · cs.LG · Submitted 2026-10-09 · Read on arXiv

cs.LG

Submitted: 2026-10-09

Updated: 2026-10-09

Terminology

• LoRA Adapters — 1× in this paper · explained in 3 episodes

Sources

• Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
• Distributed Direct Preference Optimization
• Federated LoRA with Sparse Communication
• On the Convergence of FedAvg on Non-IID Data
• FDLoRA: Personalized Federated Learning of Large Language Model via Dual LoRA Tuning
• ADKO: Agentic Decentralized Knowledge Optimization
• Improving LoRA in Privacy-preserving Federated Learning
• pFedLoRA: Model-Heterogeneous Personalized Federated Learning with LoRA Tuning
• FedPDPO: Federated Personalized Direct Preference Optimization for Large Language Model Alignment

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