@inproceedings{li-etal-2025-watermarking,
    title = "Watermarking with Low-Entropy {POS}-Guided Token Partitioning and {Z}-Score-Driven Dynamic Bias for Large Language Models",
    author = "Li, He  and
      Chen, Xiaojun  and
      Zhao, Zhendong  and
      Yang, Yunfei  and
      Zhao, Xin  and
      He, Jingcheng",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2025",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/author-page-yu-wang-polytechnic/2025.findings-emnlp.260/",
    doi = "10.18653/v1/2025.findings-emnlp.260",
    pages = "4840--4859",
    ISBN = "979-8-89176-335-7",
    abstract = "Texts generated by large language models (LLMs) are increasingly widespread online. Due to the lack of effective attribution mechanisms, the enforcement of copyright and the prevention of misuse remain significant challenges in the context of LLM-generated content. LLMs watermark emerges as a crucial technology to trace the source of AI-generated content. However, most existing watermarking methods reduce the fidelity of semantics. To address this issue, this paper introduces a novel watermarking framework. To enhance the fidelity of semantics, we propose low-entropy POS-guided token partitioning mechanism and z-score-driven dynamic bias mechanism. Moreover, to enhance the robustness against potential bias sparsity exploitation attack, we propose a relative position encoding (RPE) mechanism, which can uniformly distribute bias in the generated text. Evaluated across 6 baselines, 4 tasks, and 5 LLMs under 8 attacks, compared to the KGW, our watermark improves semantic fidelity by 24.53{\%} (RC-PPL) and robustness by 3.75{\%} (F1). Our code is publicly available, facilitating reproducibility in LLM watermarking research."
}