Reproduce “When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift” 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
Khoi Le, Tri Cao, Phong Nguyen, Cong-Duy Nguyen, Anh Tuan Luu, Miao Chunyan, See-Kiong Ng, Thong Nguyen
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.