Reliability-Weighted Direct Preference Optimization: Penalized Weights for Robust Preference Learning
stat.ML, cs.LG, stat.ME
Submitted: 2026-10-30
Updated: 2026-10-30
Terminology
Sources
- PLC-DPO: Posterior Label Correction in Noisy and Ambiguous Preference Optimization
- Penalized Weighted Least Squares for Outlier Detection and Robust Regression
- Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
Related papers
- Uniform-in-Time Weak Propagation-of-Chaos in Shallow Neural Networks
- Diffusion Models Observe Only Gradients: A Geometric Perspective on Score Matching Errors
- Quantifying Error Propagation and Model Collapse in Diffusion Models
- Behavior of prediction performance metrics with rare events
- Statistical Inference and Learning for Shapley Additive Explanations (SHAP)
- Control Variate Design for Score-Function Gradient Estimators in Importance-Weighted Variational Inference