Reproduce “Calibrating Post-Training Feature Shifts for LLM Data Contamination Detection” 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
Zhen Yang, Mengqi Wang, Gengda Zhao, Mo Zhou, Jianwei Wang, Wenjie Zhang
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.