Zhuang Li

EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions

From Corpora to Causality: Unveiling Causal Comprehension in Large Language Models

An Empirical Study on Enhancing LLMs' Alignment Capabilities through Restyled In-Context Learning Demonstration Examples

SCAR: Efficient Instruction-Tuning for Large Language Models via Style Consistency-Aware Response Ranking

IMO: Greedy Layer-Wise Sparse Representation Learning for Out-of-Distribution Text Classification with Pre-trained Models