Reproduce “Twice-Told Critiques: Claim-Level Homogenization of Peer Review in the LLM Era” 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
Ilya Gusev
The authors measure repeated problems in reviews by extracting critique claims and grouping claims about the same issue in the same paper element. Overlap is shared problems divided by the smaller critique set. At ICLR, overlap rose from 12.0% in 2026 to 21.3% in 2027; within-paper flagged-review pairs had 4.5 points more overlap, but the observational results do not establish that LLMs caused the pattern.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.