Reproduce “Safety Kernel: Mechanistic Alignment for Cross-Lingual Defense in LLMs” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Chengyu Xie, Fei Shen, Shuyi Miao, Yue Feng, Jian Yu, Pengyang Shao, Yijun Tian, Xiaoyu Du
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.