@inproceedings{li-etal-2026-beyond-final,
    title = "Beyond the Final Actor: Modeling the Dual Roles of Creator and Editor for Fine-Grained {LLM}-Generated Text Detection",
    author = "Li, Yang  and
      Sheng, Qiang  and
      Wang, Zhengjia  and
      Yang, Yehan  and
      Wang, Danding  and
      Cao, Juan",
    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.235/",
    pages = "5188--5203",
    ISBN = "979-8-89176-390-6",
    abstract = "The misuse of large language models (LLMs) requires precise detection of synthetic text. Existing works mainly follow binary or ternary classification settings, which can only distinguish pure human/LLM text or collaborative text at best. This remains insufficient for the nuanced regulation, as the LLM-polished human text and humanized LLM text often trigger different policy consequences. In this paper, we explore fine-grained LLM-generated text detection under a rigorous four-class setting. To handle such complexities, we propose RACE (Rhetorical Analysis for Creator-Editor Modeling), a fine-grained detection method that characterizes the distinct signatures of creator and editor. Specifically, RACE utilizes Rhetorical Structure Theory (RST) to construct a logic graph for the creator{'}s foundation while extracting Elementary Discourse Unit (EDU)-level features for the editor{'}s style. Experiments show that RACE outperforms 12 baselines in identifying fine-grained types with low false alarms, offering a policy-aligned solution for LLM regulation."
}