2 papers
cs.LG2025
A Mathematics Framework of Artificial Shifted Population Risk and Its Further Understanding Related to Consistency Regularization
Xiliang Yang, Shenyang Deng, Shicong Liu +3
Data augmentation is an important technique in training deep neural networks as it enhances their ability to generalize and remain robust. While data augmentation is commonly used…
cs.CL2025
DPO-Shift: Shifting the Distribution of Direct Preference Optimization
Xiliang Yang, Feng Jiang, Qianen Zhang +2
Direct Preference Optimization (DPO) and its variants have become increasingly popular for aligning language models with human preferences. These methods aim to teach models to bet…