Overview

Automated peer review studies how computational systems can evaluate manuscripts, identify weaknesses, check claims, and assist tasks such as reviewer matching, rebuttal, and meta-review. Common approaches include prompting and fine-tuning language models, retrieval-augmented and multi-agent review, rubric-based scoring, and tool-assisted checks of references, code, or experiments. Evaluation uses conference-paper datasets, expert annotations, outcome prediction, and injected-error or claim-verification benchmarks to test dimensions such as correctness, coverage, calibration, and actionability. Systems can provide useful and sometimes complementary feedback, but unreliable judgments, hallucinations, bias, and vulnerability to strategic rewriting or prompt injection leave human oversight and robust evaluation central concerns.

Latest papers

CardsList

122 papers11 papers in the last four weeks, up 10% on the four weeks before. 0.1% of all new papers.

  1. "Give a Positive Review Only": An Early Investigation Into In-Paper Prompt Injection Attacks and Defenses for AI Reviewers

    Nov 3, 2025Qin Zhou, Zhexin Zhang, Zhi Li +1Adversarial Prompt GenerationIndirect Prompt Injection

  2. Calibrated Generative AI as Meta-Reviewer: A Systemic Functional Linguistics Discourse Analysis of Reviews of Peer Reviews

    Sep 18, 2025Gabriela C. Zapata, Bill Cope, Mary Kalantzis +1Generative AI in EducationEducational Feedback Generation