4 papers
AsFT: Anchoring Safety During LLM Fine-Tuning Within Narrow Safety Basin
Shuo Yang, Qihui Zhang, Yuyang Liu +7
Fine-tuning large language models (LLMs) improves performance but introduces critical safety vulnerabilities: even minimal harmful data can severely compromise safety measures. We…
GPT as a Monte Carlo Language Tree: A Probabilistic Perspective
Kun-Peng Ning, Jia-Yu Yao, Yu-Yang Liu +2
Large Language Models (LLMs), such as GPT, are considered to learn the latent distributions within large-scale web-crawl datasets and accomplish natural language processing (NLP) t…
Sparse Orthogonal Parameters Tuning for Continual Learning
Kun-Peng Ning, Hai-Jian Ke, Yu-Yang Liu +3
Continual learning methods based on pre-trained models (PTM) have recently gained attention which adapt to successive downstream tasks without catastrophic forgetting. These method…
Is Parameter Collision Hindering Continual Learning in LLMs?
Shuo Yang, Kun-Peng Ning, Yu-Yang Liu +4
Large Language Models (LLMs) often suffer from catastrophic forgetting when learning multiple tasks sequentially, making continual learning (CL) essential for their dynamic deploym…