Detecting LLM-Generated Peer Reviews

• URL: http://arxiv.org/abs/2503.15772v2
• Date: Mon, 19 May 2025 01:40:25 GMT
• Title: Detecting LLM-Generated Peer Reviews
• Abstract summary: The rise of large language models (LLMs) has introduced concerns that some reviewers may rely on these tools to generate reviews rather than writing them independently.<n>We consider the approach of performing indirect prompt injection via the paper's PDF, prompting the LLM to embed a covert watermark in the generated review.<n>We introduce watermarking schemes and hypothesis tests that control the family-wise error rate across multiple reviews, achieving higher statistical power than standard corrections.
• Score: 37.51215252353345
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The integrity of peer review is fundamental to scientific progress, but the rise of large language models (LLMs) has introduced concerns that some reviewers may rely on these tools to generate reviews rather than writing them independently. Although some venues have banned LLM-assisted reviewing, enforcement remains difficult as existing detection tools cannot reliably distinguish between fully generated reviews and those merely polished with AI assistance. In this work, we address the challenge of detecting LLM-generated reviews. We consider the approach of performing indirect prompt injection via the paper's PDF, prompting the LLM to embed a covert watermark in the generated review, and subsequently testing for presence of the watermark in the review. We identify and address several pitfalls in na\"ive implementations of this approach. Our primary contribution is a rigorous watermarking and detection framework that offers strong statistical guarantees. Specifically, we introduce watermarking schemes and hypothesis tests that control the family-wise error rate across multiple reviews, achieving higher statistical power than standard corrections such as Bonferroni, while making no assumptions about the nature of human-written reviews. We explore multiple indirect prompt injection strategies--including font-based embedding and obfuscated prompts--and evaluate their effectiveness under various reviewer defense scenarios. Our experiments find high success rates in watermark embedding across various LLMs. We also empirically find that our approach is resilient to common reviewer defenses, and that the bounds on error rates in our statistical tests hold in practice. In contrast, we find that Bonferroni-style corrections are too conservative to be useful in this setting.

Related papers

• ActReview: Rebuttal-Guided Training Data and Rubric Rewards for Actionable Peer Review Generation [54.82704239643649]
  We introduce ActReview, a rebuttal-guided post-training framework that connects paper-specific diagnoses to concrete, grounded revision plans.<n>Our central insight is that author rebuttals reveal plausible actions for addressing reviewer concerns and can therefore provide latent supervision for revision-oriented feedback.<n>We also introduce ActReview-Bench, a human-curated benchmark of 1,000 instances for evaluating diagnostic quality and revision usefulness.
  arXiv  Detail & Related papers  (2026-09-08T17:30:16Z)
• From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent [52.42081442204093]
  We argue that a key limitation is the lack of flexibility to proactively investigate suspicious parts of a paper.<n>We propose ProReviewer, a scientific peer review agent that proactively reviews a paper guided by a maintained, structured review log.<n> Experiments show that ProReviewer with an 8B backbone, trained by supervised fine-tuning and optimized by reinforcement learning, achieves the highest average score across five quality dimensions.
  arXiv  Detail & Related papers  (2026-06-11T13:38:23Z)
• 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)
• Reviewing the Reviewer: Elevating Peer Review Quality through LLM-Guided Feedback [75.31379834079648]
  We introduce an LLM-driven framework that decomposes reviews into argumentative segments.<n>We also release LazyReviewPlus, a dataset of 1,309 sentences labeled for lazy thinking and specificity.
  arXiv  Detail & Related papers  (2026-01-17T20:32:18Z)
• Pre-review to Peer review: Pitfalls of Automating Reviews using Large Language Models [1.8349858105838042]
  Large Language Models are versatile general-task solvers, and their capabilities can truly assist people with scholarly peer review as textitpre-review agents.<n>While incredibly beneficial, automating academic peer-review, as a concept, raises concerns surrounding safety, research integrity, and the validity of the academic peer-review process.
  arXiv  Detail & Related papers  (2025-12-14T09:56:07Z)
• SWAP: Towards Copyright Auditing of Soft Prompts via Sequential Watermarking [58.475471437150674]
  We propose sequential watermarking for soft prompts (SWAP)<n>SWAP encodes watermarks through a specific order of defender-specified out-of-distribution classes.<n>Experiments on 11 datasets demonstrate SWAP's effectiveness, harmlessness, and robustness against potential adaptive attacks.
  arXiv  Detail & Related papers  (2025-11-05T13:48:48Z)
• BadScientist: Can a Research Agent Write Convincing but Unsound Papers that Fool LLM Reviewers? [21.78901120638025]
  We investigate whether fabrication-oriented paper generation agents can deceive multi-model LLM review systems.<n>Our generator employs presentation-manipulation strategies requiring no real experiments.<n>Despite provably sound aggregation mathematics, integrity checking systematically fails.
  arXiv  Detail & Related papers  (2025-10-20T18:37:11Z)
• When Your Reviewer is an LLM: Biases, Divergence, and Prompt Injection Risks in Peer Review [34.067892820832405]
  This paper presents a systematic evaluation of large language models (LLMs) as academic reviewers.<n>Using a curated dataset of 1,441 papers from ICLR 2023 and NeurIPS 2022, we evaluate GPT-5-mini against human reviewers across ratings, strengths, and weaknesses.<n>Our findings show that LLMs consistently inflate ratings for weaker papers while aligning more closely with human judgments on stronger contributions.
  arXiv  Detail & Related papers  (2025-09-12T00:57:50Z)
• The Feasibility of Topic-Based Watermarking on Academic Peer Reviews [46.71493672772134]
  We evaluate topic-based watermarking (TBW) for large language models (LLMs)<n>Our results show that TBW maintains review quality relative to non-watermarked outputs, while demonstrating strong to paraphrasing-based evasion.
  arXiv  Detail & Related papers  (2025-05-27T18:09:27Z)
• ReviewAgents: Bridging the Gap Between Human and AI-Generated Paper Reviews [26.031039064337907]
  Academic paper review is a critical yet time-consuming task within the research community.<n>With the increasing volume of academic publications, automating the review process has become a significant challenge.<n>We propose ReviewAgents, a framework that leverages large language models (LLMs) to generate academic paper reviews.
  arXiv  Detail & Related papers  (2025-03-11T14:56:58Z)
• LLM-Safety Evaluations Lack Robustness [58.334290876531036]
  We argue that current safety alignment research efforts for large language models are hindered by many intertwined sources of noise.<n>We propose a set of guidelines for reducing noise and bias in evaluations of future attack and defense papers.
  arXiv  Detail & Related papers  (2025-03-04T12:55:07Z)
• PredictaBoard: Benchmarking LLM Score Predictability [50.47497036981544]
  Large Language Models (LLMs) often fail unpredictably.<n>This poses a significant challenge to ensuring their safe deployment.<n>We present PredictaBoard, a novel collaborative benchmarking framework.
  arXiv  Detail & Related papers  (2025-02-20T10:52:38Z)
• Are We There Yet? Revealing the Risks of Utilizing Large Language Models in Scholarly Peer Review [66.73247554182376]
  Large language models (LLMs) have led to their integration into peer review.<n>The unchecked adoption of LLMs poses significant risks to the integrity of the peer review system.<n>We show that manipulating 5% of the reviews could potentially cause 12% of the papers to lose their position in the top 30% rankings.
  arXiv  Detail & Related papers  (2024-12-02T16:55:03Z)
• Is Your Paper Being Reviewed by an LLM? Investigating AI Text Detectability in Peer Review [8.606381080620789]
  We investigate the ability of existing AI text detection algorithms to distinguish between peer reviews written by humans and different state-of-the-art LLMs.<n>Our analysis shows that existing approaches fail to identify many GPT-4o written reviews without also producing a high number of false positive classifications.<n>We propose a new detection approach which surpasses existing methods in the identification of GPT-4o written peer reviews at low levels of false positive classifications.
  arXiv  Detail & Related papers  (2024-10-03T22:05:06Z)
• AI-Driven Review Systems: Evaluating LLMs in Scalable and Bias-Aware Academic Reviews [18.50142644126276]
  We evaluate the alignment of automatic paper reviews with human reviews using an arena of human preferences by pairwise comparisons. We fine-tune an LLM to predict human preferences, predicting which reviews humans will prefer in a head-to-head battle between LLMs. We make the reviews of publicly available arXiv and open-access Nature journal papers available online, along with a free service which helps authors review and revise their research papers and improve their quality.
  arXiv  Detail & Related papers  (2024-08-19T19:10:38Z)
• Identifying Inaccurate Descriptions in LLM-generated Code Comments via Test Execution [11.418182511485032]
  We evaluate comments generated by three Large Language Models (LLMs) We propose the concept of document testing, in which a document is verified by using an LLM to generate tests based on the document, running those tests, and observing whether they pass or fail.
  arXiv  Detail & Related papers  (2024-06-21T02:40:34Z)
• WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia [59.96425443250666]
  Retrieval-augmented generation (RAG) has emerged as a promising solution to mitigate the limitations of large language models (LLMs) In this work, we conduct a comprehensive evaluation of LLM-generated answers to questions based on contradictory passages from Wikipedia. We benchmark a diverse range of both closed and open-source LLMs under different QA scenarios, including RAG with a single passage, and RAG with 2 contradictory passages.
  arXiv  Detail & Related papers  (2024-06-19T20:13:42Z)
• Pride and Prejudice: LLM Amplifies Self-Bias in Self-Refinement [75.7148545929689]
  Large language models (LLMs) improve their performance through self-feedback on certain tasks while degrade on others. We formally define LLM's self-bias - the tendency to favor its own generation. We analyze six LLMs on translation, constrained text generation, and mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2024-02-18T03:10:39Z)
• PRE: A Peer Review Based Large Language Model Evaluator [14.585292530642603]
  Existing paradigms rely on either human annotators or model-based evaluators to evaluate the performance of LLMs. We propose a novel framework that can automatically evaluate LLMs through a peer-review process.
  arXiv  Detail & Related papers  (2024-01-28T12:33:14Z)
• Fake Alignment: Are LLMs Really Aligned Well? [91.26543768665778]
  This study investigates the substantial discrepancy in performance between multiple-choice questions and open-ended questions. Inspired by research on jailbreak attack patterns, we argue this is caused by mismatched generalization.
  arXiv  Detail & Related papers  (2023-11-10T08:01:23Z)
• Assessing the Reliability of Large Language Model Knowledge [78.38870272050106]
  Large language models (LLMs) have been treated as knowledge bases due to their strong performance in knowledge probing tasks. How do we evaluate the capabilities of LLMs to consistently produce factually correct answers? We propose MOdel kNowledge relIabiliTy scORe (MONITOR), a novel metric designed to directly measure LLMs' factual reliability.
  arXiv  Detail & Related papers  (2023-10-15T12:40:30Z)

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.