Reproduce “Probing the Safety Response Boundary of Large Language Models via Unsafe Decoding Path Generation” 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

Haoyu Wang, Bingzhe Wu, Yatao Bian, Yongzhe Chang, Xueqian Wang, Peilin Zhao

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.