Reproduce “Provable Defense Framework for LLM Jailbreaks via Noise-Augumented Alignment” 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
Zehua Cheng, Jianwei Yang, Wei Dai, Jiahao Sun
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.