We introduce a low-resource safety enhancement method for aligning large language models (LLMs) without the need for supervised fine-tuning (SFT) or reinforcement learning from human feedback (RLHF). Our main idea is to exploit knowledge distillation to extract the alignment information from existing well-aligned LLMs and integrate it into unaligned LLMs in a plug-and-play fashion. Methodology, we employ delta debugging to identify the critical components of knowledge necessary for effective distillation. On the harmful question dataset, our method significantly enhances the average defense success rate by approximately 14.41%, reaching as high as 51.39%, in 17 unaligned pre-trained LLMs, without compromising performance.
@article{arxiv.2406.01514,
title = {Decoupled Alignment for Robust Plug-and-Play Adaptation},
author = {Haozheng Luo and Jiahao Yu and Wenxin Zhang and Jialong Li and Jerry Yao-Chieh Hu and Xinyu Xing and Han Liu},
journal= {arXiv preprint arXiv:2406.01514},
year = {2024}
}