Reproduce “TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning” 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

Xuanli He, Jun Wang, Qiongkai Xu, Pasquale Minervini, Pontus Stenetorp, Benjamin I. P. Rubinstein, Trevor Cohn

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