1

A training-free method that robustifies LLM safety alignment against fine-tuning by extrapolating low-rank safety subspaces, significantly reducing attack success rates while preserving model utility.

A study revealing safety-specific pitfalls of multi-model synthetic preference data in DPO alignment.

The first automated guardrail for agents.

A training-free approach that calibrates chain-of-thought reasoning in LLMs, improving accuracy while reducing computational overhead.

We examined how superficial LLM alignments are thru a linear distillation method.

We develop a chatbot for reminiscence therapy

A comprehensive privacy assessment of LLMs.

A comprehensive trustworthiness assessment of compressed LLMs.

Zeroth-order optimization for LLM.

Recent advances in unsupervised learning have shown that unsupervised pre-training, followed by fine-tuning, can improve model generalization. However, a rigorous understanding of how the representation function learned on an unlabeled dataset …