@inproceedings{chen-etal-2026-coconuts,
    title = "{C}o{C}o{NUTS}: Concentrating on Content while Neglecting Uninformative Textual Styles for {AI}-Generated Peer Review Detection",
    author = "Chen, Yihan  and
      Chen, Jiawei  and
      Mo, Guozhao  and
      Chen, Xuanang  and
      He, Ben  and
      Han, Xianpei  and
      Sun, Le",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1240/",
    pages = "26921--26950",
    ISBN = "979-8-89176-390-6",
    abstract = "The growing use of large language models (LLMs) in peer review threatens scholarly integrity. Recent conference policies allow AI tools for language polishing but prohibit their use for generating substantive content. However, existing detectors mainly rely on stylistic cues, making it difficult to distinguish between surface-level language refinement and genuine content generation. To address this, we advocate a content-based detection paradigm and introduce CoCoNUTS, a comprehensive benchmark containing 315,535 reviews covering leading AI conferences and six human-AI collaboration modes. Our evaluation shows that current detectors struggle to handle these nuanced settings. Consequently, we propose CoCoDet, an AI review detector designed to identify substantive AI-generation. Experiments demonstrate that CoCoDet achieves a macro F1-score of 98.24{\%}. Crucially, on permissible machine-polished reviews, it maintains a low false positive rate of 3.89{\%}, substantially outperforming the strongest baseline (7.84{\%}). Examination on real-world reviews using CoCoDet reveals an escalating trend of substantive AI generation. Our work exposes the inadequacy of current detectors, underscoring the importance of domain-specific solutions."
}