Reproduce “Legend: Leveraging Representation Engineering to Annotate Safety Margin for Preference Datasets” 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

Duanyu Feng, Bowen Qin, Chen Huang, Youcheng Huang, Zheng Zhang, Wenqiang Lei

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