Reproduce “The Art of Defending: A Systematic Evaluation and Analysis of LLM Defense Strategies on Safety and Over-Defensiveness” 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
Neeraj Varshney, Pavel Dolin, Agastya Seth, Chitta Baral
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.