1. Aspect-Guided Multi-Level Perturbation Analysis of Large Language Models in Automated Peer Review

   http://arxiv.org/abs/2502.12510v1 · arxiv

   We propose an aspect-guided, multi-level perturbation framework to evaluate the robustness of Large Language Models (LLMs) in automated peer review. Our framework explores perturbations in three key components of the peer review process-papers, reviews, and rebuttals-across several quality aspects,

2. AI-Assisted Peer Review Across Research Communities: From Reviewer AI Policies to LLM Review Quality

   http://arxiv.org/abs/2608.03581v1 · arxiv

   AI-assisted peer review is increasingly discussed and adopted as a tool to support the scientific publishing process, yet there is little systematic understanding of how publication venues regulate its use or of how capable current AI review systems are. We address these questions by first surveying

3. Effectiveness of Anonymization in Double-Blind Review

   http://arxiv.org/abs/1709.01609v1 · arxiv

   Double-blind review relies on the authors' ability and willingness to effectively anonymize their submissions. We explore anonymization effectiveness at ASE 2016, OOPSLA 2016, and PLDI 2016 by asking reviewers if they can guess author identities. We find that 74%-90% of reviews contain no correct gu

4. Peer Review as A Multi-Turn and Long-Context Dialogue with Role-Based Interactions

   http://arxiv.org/abs/2406.05688v1 · arxiv

   Large Language Models (LLMs) have demonstrated wide-ranging applications across various fields and have shown significant potential in the academic peer-review process. However, existing applications are primarily limited to static review generation based on submitted papers, which fail to capture t

5. Review on ferroelectric/polar metals

   http://arxiv.org/abs/2007.11200v1 · arxiv

   The possibility of reconciliation between seemingly mutually exclusive properties in one system can not only lead to theoretical breakthroughs but also potential novel applications. The research on the coexistence of two purportedly contra-indicated properties, ferroelectricity/polarity and conducti

6. Previously on... Automating Code Review

   http://arxiv.org/abs/2508.18003v1 · arxiv

   Modern Code Review (MCR) is a standard practice in software engineering, yet it demands substantial time and resource investments. Recent research has increasingly explored automating core review tasks using machine learning (ML) and deep learning (DL). As a result, there is substantial variability

7. Optimizing Peer Grading: A Systematic Literature Review of Reviewer Assignment Strategies and Quantity of Reviewers

   http://arxiv.org/abs/2508.11678v2 · arxiv

   Peer assessment has established itself as a critical pedagogical tool in academic settings, offering students timely, high-quality feedback to enhance learning outcomes. However, the efficacy of this approach depends on two factors: (1) the strategic allocation of reviewers and (2) the number of rev

8. Partition function of 1-, 2-, and 3-D monatomic ideal gas: A simple and comprehensive review

   http://arxiv.org/abs/1106.1273v2 · arxiv

   This article discusses partition function of monatomic ideal gas which is given in Statistical Physisc at Physics Department, Faculty of Mathematics and Natural Sciences, Institut Teknologi Bandung, Indonesia. Students in general are not familiar with partition function. This unfamiliarness was dete

9. Systematic Review of Approaches to Improve Peer Assessment at Scale

   http://arxiv.org/abs/2001.10617v1 · arxiv

   Peer Assessment is a task of analysis and commenting on student's writing by peers, is core of all educational components both in campus and in MOOC's. However, with the sheer scale of MOOC's & its inherent personalised open ended learning, automatic grading and tools assisting grading at scale is h

10. When AI Reviews Its Own Code: Recursive Self-Training Collapse in Code LLMs

    http://arxiv.org/abs/2606.28438v1 · arxiv

    Recursive self-training can degrade neural generative models when generated data is reused without fresh human data or external quality control. We study this risk in code LLMs, where AI-generated code can enter real repositories, later become training data, and create a repository-scale self-traini

10 hasil · 875 md