@inproceedings{wang-etal-2026-human,
    title = "Is Human-Like Text Liked by Humans? Multilingual Human Detection and Preference Against {AI}",
    author = "Wang, Yuxia  and
      Xing, Rui  and
      Mansurov, Jonibek  and
      Puccetti, Giovanni  and
      Xie, Zhuohan  and
      Ta, Minh Ngoc  and
      Geng, Jiahui  and
      Su, Jinyan  and
      Abassy, Mervat  and
      Eletter, Saadeldine  and
      Elozeiri, Kareem  and
      Laiyk, Nurkhan  and
      Goloburda, Maiya  and
      Mahmoud, Tarek  and
      Tomar, Raj Vardhan  and
      Aziz, Alexander  and
      Koike, Ryuto  and
      Kaneko, Masahiro  and
      Shelmanov, Artem  and
      Artemova, Ekaterina  and
      Mikhailov, Vladislav  and
      Tsvigun, Akim  and
      Aji, Alham Fikri  and
      Habash, Nizar  and
      Gurevych, Iryna  and
      Nakov, Preslav",
    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.639/",
    pages = "14043--14076",
    ISBN = "979-8-89176-390-6",
    abstract = "Prior studies have shown that distinguishing text generated by Large Language Models (LLMs) from human-written one is highly challenging for humans, and often no better than random guessing. To verify the generalizability of this finding across languages and domains, we perform an extensive case study to identify the upper bound of human detection accuracy. Across 16 datasets covering 9 languages and 9 domains, 19 annotators achieved an average detection accuracy of 87.6{\%}, thus challenging previous conclusions. We find that major gaps between human and machine text lie in concreteness, cultural nuances, and diversity. Prompting by explicitly explaining the distinctions in the prompts can partially bridge the gaps in over 50{\%} of the cases. However, we also find that humans do not always prefer human-written text, particularly when they cannot clearly identify its source. We release our dataset, the human labels, and the annotator metadata at https://github.com/xnlp-lab/HumanEval-MGT."
}