3 papers
cs.LG2026
Safeguarding LLM Fine-tuning via Push-Pull Distributional Alignment
Haozhong Wang, Zhuo Li, Yibo Yang +3
The inherent safety alignment of Large Language Models (LLMs) is prone to erosion during fine-tuning, even when using seemingly innocuous datasets. While existing defenses attempt…
cs.LG2025
Deep Neural Network Calibration by Reducing Classifier Shift with Stochastic Masking
Jiani Ni, He Zhao, Yibo Yang +1
In recent years, deep neural networks (DNNs) have shown competitive results in many fields. Despite this success, they often suffer from poor calibration, especially in safety-crit…
cs.LG2025
Balancing Two Classifiers via A Simplex ETF Structure for Model Calibration
Jiani Ni, He Zhao, Jintong Gao +2
In recent years, deep neural networks (DNNs) have demonstrated state-of-the-art performance across various domains. However, despite their success, they often face calibration issu…