Large Language Models (LLMs) often memorize sensitive, private, or copyrighted data
during pre-training. LLM unlearning aims to eliminate the influence of undesirable data from …

Large Language Models (LLMs) are often aligned using contrastive alignment objectives
and preference pair datasets. The interaction between model, paired data, and objective …

Large language model unlearning has gained increasing attention due to its potential to
mitigate security and privacy concerns. Current research predominantly focuses on Instance …

Large language models (LLMs) excel in various capabilities but also pose safety risks such
as generating harmful content and misinformation, even after safety alignment. In this paper …