Peer review serves as a backbone of academic research, but in most AI conferences, the review quality is degrading as the number of submissions explodes. To reliably detect low-quality reviews, we define misinformed review points as either "weaknesses" in a review that contain incorrect premises, or "questions" in a review that can be already answered by the paper. We verify that 15.2% of weaknesses and 26.4% of questions are misinformed and introduce ReviewScore indicating if a review point is misinformed. To evaluate the factuality of each premise of weaknesses, we propose an automated engine that reconstructs every explicit and implicit premise from a weakness. We build a human expert-annotated ReviewScore dataset to check the ability of LLMs to automate ReviewScore evaluation. Then, we measure human-model agreements on ReviewScore using eight current state-of-the-art LLMs. The models show F1 scores of 0.4--0.5 and kappa scores of 0.3--0.4, indicating moderate agreement but also suggesting that fully automating the evaluation remains challenging. A thorough disagreement analysis reveals that most errors are due to models' incorrect reasoning. We also prove that evaluating premise-level factuality shows significantly higher agreements than evaluating weakness-level factuality.
@article{arxiv.2509.21679,
title = {ReviewScore: Misinformed Peer Review Detection with Large Language Models},
author = {Hyun Ryu and Doohyuk Jang and Hyemin S. Lee and Joonhyun Jeong and Gyeongman Kim and Donghyeon Cho and Gyouk Chu and Minyeong Hwang and Hyeongwon Jang and Changhun Kim and Haechan Kim and Jina Kim and Joowon Kim and Yoonjeon Kim and Kwanhyung Lee and Chanjae Park and Heecheol Yun and Gregor Betz and Eunho Yang},
journal= {arXiv preprint arXiv:2509.21679},
year = {2026}
}