作者位次 #16/26ACL 2026Poster· Natural Language Processing
Is Human-Like Text Liked by Humans? Multilingual Human Detection and Preference Against AI
Yuxia Wang · Rui Xing · Jonibek Mansurov · Giovanni Puccetti · Zhuohan Xie · Minh Ngoc Ta · Jiahui Geng · Jinyan Su · Mervat Abassy · Saadeldine Eletter · Kareem Elozeiri · Nurkhan Laiyk · Maiya Goloburda · Tarek Mahmoud · Raj Vardhan Tomar · Alexander Aziz · Ryuto Koike · Masahiro Kaneko · Artem Shelmanov · Ekaterina Artemova · Vladislav Mikhailov · Akim Tsvigun · Alham Fikri Aji · Nizar Habash · Iryna Gurevych · Preslav Nakov
摘要
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...