@inproceedings{li-etal-2025-prdetect,
    title = "{PRD}etect: Perturbation-Robust {LLM}-generated Text Detection Based on Syntax Tree",
    author = "Li, Xiang  and
      Yin, Zhiyi  and
      Tan, Hexiang  and
      Jing, Shaoling  and
      Su, Du  and
      Cheng, Yi  and
      Shen, Huawei  and
      Sun, Fei",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2025",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.findings-naacl.464/",
    pages = "8290--8301",
    ISBN = "979-8-89176-195-7",
    abstract = "As LLM-generated text becomes increasingly prevalent on the internet, often containing hallucinations or biases, detecting such content has emerged as a critical area of research.Recent methods have demonstrated impressive performance in detecting text generated entirely by LLMs.However, in real-world scenarios, users often introduce perturbations to the LLM-generated text, and the robustness of existing detection methods against these perturbations has not been sufficiently explored.This paper empirically investigates this challenge and finds that even minor perturbations can severely degrade the performance of current detection methods. To address this issue, we find that the syntactic tree is minimally affected by disturbances and exhibits distinct differences between human-written and LLM-generated text.Therefore, we propose a detection method based on syntactic trees, which can capture features invariant to perturbations.It demonstrates significantly improved robustness against perturbation on the HC3 and GPT-3.5-mixed datasets.Moreover, it also has the shortest time expenditure.We provide the code and data at https://github.com/thulx18/PRDetect."
}