Reproduce “Training-Free Policy Violation Detection via Activation-Space Whitening 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

Oren Rachmil, Avishag Shapira, Roy Betser, Omer Hofman, Itay Gershon, Asaf Shabtai, Yuval Elovici, Roman Vainshtein

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