Reproduce “Refusal Is Not Robustness: Measuring Harmful Reachability in Autoregressive Language Models” 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
Parv Kapoor, Teresa Fortes, Claudia Mamede, Rui Abreu, Jonathan Aldrich, Eunsuk Kang
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.