List your company

Direct Preference Optimization on UltraFeedback

69.92AccuracyFedPDPO
63.648865.276966.90568.5331Mar 20, 2026

Evaluation results

MethodLinks
FedPDPODomain Setting (Cross-Domain)=Cross-Domain, Optimization Objective (PPO/DPO)=DPO2026.0369.92
FedPerDomain Setting (Cross-Domain)=Cross-Domain, Optimization Objective (PPO/DPO)=DPO2026.0368.02
Per-FedAvgDomain Setting (Cross-Domain)=Cross-Domain, Optimization Objective (PPO/DPO)=DPO2026.0367.48
FedRepDomain Setting (Cross-Domain)=Cross-Domain, Optimization Objective (PPO/DPO)=DPO2026.0367.25
FedAvgDomain Setting (Cross-Domain)=Cross-Domain, Optimization Objective (PPO/DPO)=DPO2026.0366.45
FedRepDomain Setting (Cross-Domain)=Cross-Domain, Optimization Objective (PPO/DPO)=PPO2026.0365.54
FedAMPDomain Setting (Cross-Domain)=Cross-Domain, Optimization Objective (PPO/DPO)=DPO2026.0365.47
FedPerDomain Setting (Cross-Domain)=Cross-Domain, Optimization Objective (PPO/DPO)=PPO2026.0365.45
Per-FedAvgDomain Setting (Cross-Domain)=Cross-Domain, Optimization Objective (PPO/DPO)=PPO2026.0364.67
FedAMPDomain Setting (Cross-Domain)=Cross-Domain, Optimization Objective (PPO/DPO)=PPO2026.0363.98
FedAvgDomain Setting (Cross-Domain)=Cross-Domain, Optimization Objective (PPO/DPO)=PPO2026.0363.89