PeerPrism: Peer Evaluation Expertise vs Review-writing AI

• URL: http://arxiv.org/abs/2604.14513v1
• Date: Thu, 16 Apr 2026 00:59:55 GMT
• Title: PeerPrism: Peer Evaluation Expertise vs Review-writing AI
• Abstract summary: We introduce PeerPrism, a benchmark of 20,690 peer reviews explicitly designed to disentangle idea provenance from text provenance.<n>We benchmark state-of-the-art LLM text detection methods on PeerPrism.<n>Our results show that current detection methods conflate surface realization with intellectual contribution.
• Score: 12.533035088439975
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Models (LLMs) are increasingly used in scientific peer review, assisting with drafting, rewriting, expansion, and refinement. However, existing peer-review LLM detection methods largely treat authorship as a binary problem-human vs. AI-without accounting for the hybrid nature of modern review workflows. In practice, evaluative ideas and surface realization may originate from different sources, creating a spectrum of human-AI collaboration. In this work, we introduce PeerPrism, a large-scale benchmark of 20,690 peer reviews explicitly designed to disentangle idea provenance from text provenance. We construct controlled generation regimes spanning fully human, fully synthetic, and multiple hybrid transformations. This design enables systematic evaluation of whether detectors identify the origin of the surface text or the origin of the evaluative reasoning. We benchmark state-of-the-art LLM text detection methods on PeerPrism. While several methods achieve high accuracy on the standard binary task (human vs. fully synthetic), their predictions diverge sharply under hybrid regimes. In particular, when ideas originate from humans but the surface text is AI-generated, detectors frequently disagree and produce contradictory classifications. Accompanied by stylometric and semantic analyses, our results show that current detection methods conflate surface realization with intellectual contribution. Overall, we demonstrate that LLM detection in peer review cannot be reduced to a binary attribution problem. Instead, authorship must be modeled as a multidimensional construct spanning semantic reasoning and stylistic realization. PeerPrism is the first benchmark evaluating human-AI collaboration in these settings. We release all code, data, prompts, and evaluation scripts to facilitate reproducible research at https://github.com/Reviewerly-Inc/PeerPrism.

Related papers

• Sem-Detect: Semantic Level Detection of AI Generated Peer-Reviews [11.21278193949403]
  We propose Sem-Detect, an authorship detection method for peer reviews.<n>It compares a target review against multiple AI-generated reviews of the same paper.<n>It is able to distinguish fully AI reviews from authentic human-written ones.
  arXiv  Detail & Related papers  (2026-05-20T20:19:16Z)
• AI for Auto-Research: Roadmap & User Guide [107.0834449839233]
  We present an end-to-end analysis of AI across the complete research lifecycle.<n>We identify a sharp, stage-dependent boundary between reliable assistance and unreliable autonomy.<n>We show that greater automation can obscure rather than eliminate failure modes.
  arXiv  Detail & Related papers  (2026-05-18T17:08:26Z)
• 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)
• Policies Permitting LLM Use for Polishing Peer Reviews Are Currently Not Enforceable [17.525659482226875]
  A number of scientific conferences and journals have recently enacted policies that prohibit LLM usage by peer reviewers.<n>We assemble a dataset of peer reviews simulating multiple levels of human-AI collaboration, and evaluate five state-of-the-art detectors.<n>Our analysis shows that all detectors misclassify a non-trivial fraction of LLM-polished reviews as AI-generated, risking false accusations of academic misconduct.
  arXiv  Detail & Related papers  (2026-03-20T19:28:34Z)
• ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review [48.60540055009675]
  ScholarPeer is a search-enabled multi-agent framework designed to emulate the cognitive processes of a senior researcher.<n>We evaluate ScholarPeer on DeepReview-13K and the results demonstrate that ScholarPeer achieves significant win-rates against state-of-the-art approaches in side-by-side evaluations.
  arXiv  Detail & Related papers  (2026-01-30T06:54:55Z)
• Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection [71.59834293521074]
  We develop a framework to distinguish between human-authored and machine-generated text.<n>Our method achieves 98.3% AUROC and AUPR with only 8.9% FPR95 on DeepFake dataset.<n>Code, pretrained weights, and demo will be released.
  arXiv  Detail & Related papers  (2025-10-07T08:14:45Z)
• CoCoNUTS: Concentrating on Content while Neglecting Uninformative Textual Styles for AI-Generated Peer Review Detection [60.52240468810558]
  We introduce CoCoNUTS, a content-oriented benchmark built upon a fine-grained dataset of AI-generated peer reviews.<n>We also develop CoCoDet, an AI review detector via a multi-task learning framework, to achieve more accurate and robust detection of AI involvement in review content.
  arXiv  Detail & Related papers  (2025-08-28T06:03:11Z)
• Is Your Paper Being Reviewed by an LLM? Benchmarking AI Text Detection in Peer Review [6.20631177269082]
  A new risk to the peer review process is that negligent reviewers will rely on large language models (LLMs) to review a paper.<n>We introduce a comprehensive dataset containing a total of 788,984 AI-written peer reviews paired with corresponding human reviews.<n>We use this new resource to evaluate the ability of 18 existing AI text detection algorithms to distinguish between peer reviews fully written by humans and different state-of-the-art LLMs.
  arXiv  Detail & Related papers  (2025-02-26T23:04:05Z)
• ExaGPT: Example-Based Machine-Generated Text Detection for Human Interpretability [62.285407189502216]
  Detecting texts generated by Large Language Models (LLMs) could cause grave mistakes due to incorrect decisions.<n>We introduce ExaGPT, an interpretable detection approach grounded in the human decision-making process.<n>We show that ExaGPT massively outperforms prior powerful detectors by up to +40.9 points of accuracy at a false positive rate of 1%.
  arXiv  Detail & Related papers  (2025-02-17T01:15:07Z)
• Forging the Forger: An Attempt to Improve Authorship Verification via Data Augmentation [52.72682366640554]
  Authorship Verification (AV) is a text classification task concerned with inferring whether a candidate text has been written by one specific author or by someone else. It has been shown that many AV systems are vulnerable to adversarial attacks, where a malicious author actively tries to fool the classifier by either concealing their writing style, or by imitating the style of another author.
  arXiv  Detail & Related papers  (2024-03-17T16:36:26Z)
• Towards Automatic Boundary Detection for Human-AI Collaborative Hybrid Essay in Education [10.606131520965604]
  This study investigates AI content detection in a rarely explored yet realistic setting. We first formalized the detection task as identifying the transition points between human-written content and AI-generated content. We then proposed a two-step approach where we separated AI-generated content from human-written content during the encoder training process.
  arXiv  Detail & Related papers  (2023-07-23T08:47:51Z)

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.