Tag
A NeurIPS reviewer reports encountering a paper and rebuttals that appear entirely LLM-generated, expressing frustration and seeking advice on how to evaluate such submissions.
Introduces TADDLE, a tool-augmented agent for detecting deficient LLM-generated peer reviews, along with an expert-annotated benchmark of 1,800 reviews on 50 ICLR 2025 papers. The system decomposes detection into four specialized analysis tools and uses two-stage semi-supervised learning for binary and multi-label classification.