Reproduce “Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning” 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

Wassim Bouaziz, Mathurin Videau, Nicolas Usunier, El-Mahdi El-Mhamdi

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