On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists

• URL: http://arxiv.org/abs/2605.20668v1
• Date: Wed, 20 May 2026 03:33:55 GMT
• Title: On the limits and opportunities of AI reviewers: Reviewing the reviews of Nature-family papers with 45 expert scientists
• Abstract summary: Many scientists view AI reviewers as probabilistic systems without the expertise to evaluate research.<n>Existing evaluations of AI reviewers have focused on whether their verdicts match human verdicts.
• Score: 113.03797263688519
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: With the advancement of AI capabilities, AI reviewers are beginning to be deployed in scientific peer review, yet their capability and credibility remain in question: many scientists simply view them as probabilistic systems without the expertise to evaluate research, while other researchers are more optimistic about their readiness without concrete evidence. Understanding what AI reviewers do well, where they fall short, and what challenges remain is essential. However, existing evaluations of AI reviewers have focused on whether their verdicts match human verdicts (e.g., score alignment, acceptance prediction), which is insufficient to characterize their capabilities and limits. In this paper, we close this gap through a large-scale expert annotation study, in which 45 domain scientists in Physical, Biological, and Health Sciences spent 469 hours rating 2,960 individual criticisms (each targeting one specific aspect of a paper) from human-written and AI-generated reviews of 82 Nature-family papers on correctness, significance, and sufficiency of evidence. On a composite of all three dimensions, a reviewing agent powered by GPT-5.2 scores above each paper's top-rated human reviewer (60.0% vs. 48.2%, p = 0.009), while all three AI reviewers (including Gemini 3.0 Pro and Claude Opus 4.5) exceed the lowest-rated human across every dimension. AI reviewers' accurate criticisms are also more often rated significant and well-evidenced, and surface a distinct 26% of issues no human raises. However, AI reviewers overlap far more than humans do (21% vs. 3% for cross-reviewer pairs), and exhibit 16 recurring weaknesses humans do not share, such as limited subfield knowledge, lack of long context management over multiple files, and overly critical stance on minor issues. Overall, our results position current AI reviewers as complements to, not substitutes for, human reviewers.

Related papers

• PaperDoctor: Evidence-Grounded and Actionable Feedback for Scientific Papers in Progress [130.58520199343707]
  PaperDoctor is an agent framework for pre-submission feedback with three key innovations.<n>First, a holistic hierarchical framework evaluates writing, layout, references, code, theory, prior work, and experiments.<n>Second, each finding contains an observation, a pointer to specific evidence such as a sentence, equation, or code line, and a revision suggestion.<n>Third, PaperDoctor selectively rebuilds and reruns experiments based on claim importance and compute budget.
  arXiv  Detail & Related papers  (2026-09-15T11:08:11Z)
• Gaming AI-Assisted Peer Reviews Poses New Risks to the Scientific Community [33.39468805524881]
  We show that AI-mediated peer review is vulnerable to a simple, low-cost manipulation.<n>We see this across disciplines and publication venues, for both human-written and AI-generated papers.<n>Our results suggest that AI tools should not be treated as neutral evaluators in high-stakes peer review.
  arXiv  Detail & Related papers  (2026-06-08T20:38:06Z)
• To Trust or Not to Trust: Authors' Response to AI-based Reviews [1.0435741631709405]
  This paper reports findings from two independent pilot studies on authors' use and perceptions of AI-based auxiliary review.<n>Author support for future use was strongest when AI was framed as a supervised or author-controlled tool.
  arXiv  Detail & Related papers  (2026-05-15T20:43:55Z)
• Stop Automating Peer Review Without Rigorous Evaluation [51.53099943385505]
  This position paper argues that today's AI systems should not be used to produce paper reviews.<n>We identify two critical issues: 1) AI reviewers exhibit a hivemind effect of excessive agreement within and across papers that reduces perspective diversity.<n>We argue that addressing the peer review crisis requires a science of peer review automation.
  arXiv  Detail & Related papers  (2026-05-04T22:41:04Z)
• When AI reviews science: Can we trust the referee? [73.47745294608072]
  We map attacks across the review lifecycle -- training and data retrieval, desk review, deep review, rebuttal, and system-level.<n>We use two advanced LLM-based referees to isolate the causal effects of prestige framing, assertion strength, rebuttal sycophancy, and contextual poisoning on review scores.
  arXiv  Detail & Related papers  (2026-04-26T08:03:32Z)
• AI-Assisted Peer Review at Scale: The AAAI-26 AI Review Pilot [45.90272517740283]
  We report the first large-scale field deployment of AI-assisted peer review.<n>Every main-track submission at AAAI-26 received one clearly identified AI review from a state-of-the-art system.
  arXiv  Detail & Related papers  (2026-04-15T14:51:07Z)
• Everyone prefers human writers, including AI [0.0]
  We conducted experiments using Raymond Queneaus Exercises Style (1947) to measure attribution bias.<n>Humans showed +13.7 percentage point (pp) bias (Cohen's h = 0.28, 95% CI: 0.21-0.34), while AI models showed +34.3 percentage point bias (h = 0.70, 95% CI: 0.65-0.76), a 2.5-fold stronger effect.
  arXiv  Detail & Related papers  (2025-10-09T21:33:30Z)
• AI Debate Aids Assessment of Controversial Claims [73.8907110799657]
  We study whether AI debate can guide biased judges toward the truth by having two AI systems debate opposing sides of controversial factuality claims.<n>In Study I, debate consistently improves human judgment accuracy and confidence calibration, outperforming consultancy.<n>In Study II, AI judges with human-like personas achieve even higher accuracy (78.5%) than human judges (70.1%) and default AI judges without personas (69.8%)<n>These findings highlight AI debate as a promising path toward scalable, bias-resilient oversight in contested domains.
  arXiv  Detail & Related papers  (2025-06-02T19:01:53Z)
• The Great AI Witch Hunt: Reviewers Perception and (Mis)Conception of Generative AI in Research Writing [36.188062803005515]
  Generative AI (GenAI) use in research writing is growing fast.<n>It is unclear how peer reviewers recognize or misjudge AI-augmented manuscripts.<n>Our findings indicate that while AI-augmented writing improves readability, language diversity, and informativeness, it often lacks research details and reflective insights from authors.
  arXiv  Detail & Related papers  (2024-06-27T02:38:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.