Co-occurring keywords · papers mentioning both
Papers
A Unified Theoretical Analysis of Private and Robust Offline Alignment: from RLHF to DPO
ICML 2025
Beyond Online Sampling: Bridging Offline-to-Online Alignment via Dynamic Data Transformation for LLMs
EMNLP 2025
Energy-Based Preference Model Offers Better Offline Alignment than the Bradley-Terry Preference Model
ICML 2025
Learn Your Reference Model for Real Good Alignment
ICLR 2025
Square$χ$PO: Differentially Private and Robust $χ^2$-Preference Optimization in Offline Direct Alignment
ICML 2025
Generalized Preference Optimization: A Unified Approach to Offline Alignment
ICML 2024