Reproduce “The Benchmark Illusion: Pruned LLMs Can Pass Multiple Choice but Fail to Answer” 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
Rui Wen, Lu Sun, Jiayang Liu, Zesheng Xu, Tianshuo Cong, Zheng Li
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.