arXiv:2508.01656v2 Announce Type: replace 
Abstract: As Large Language Models (LLMs) have reached human-like fluency and coherence, distinguishing machine-generated text (MGT) from human-written content becomes increasingly difficult. While early efforts in MGT detection have focused on binary classification, the growing landscape and diversity of LLMs require a more fine-grained yet challenging authorship attribution (AA), i.e., being able to identify the precise generator (LLM or human) behind a text. However, AA remains nowadays confined to a monolingual setting, with English being the most investigated one, overlooking the multilingual nature and usage of modern LLMs. In this work, we introduce the problem of Multilingual Authorship Attribution, which involves attributing texts to human or multiple LLM generators across diverse languages. Focusing on 18 languages -- covering multiple families and writing scripts -- and 8 generators (7 LLMs and the human-authored class), we investigate the multilingual suitability of monolingual AA methods in terms of their cross-lingual transferability, and the impact of generators on attribution performance. Our results reveal that while certain monolingual AA methods can be adapted to multilingual settings, significant limitations and challenges remain, particularly in transferring across diverse language families, underscoring the complexity of multilingual AA and the need for more robust approaches to better match real-world scenarios.

أدت التطورات الأخيرة في نماذج اللغة الكبيرة (LLMs) إلى صعوبة متزايدة في التمييز بين النصوص التي تولدها الآلات وتلك التي يكتبها البشر، مما دفع إلى التركيز على نسبة التأليف متعددة اللغات (AA). تهدف هذه الطريقة إلى تحديد الجهة المحددة التي تولد النصوص عبر 18 لغة، مما يعالج قيود أساليب AA أحادية اللغة الحالية.

Los avances recientes en los Modelos de Lenguaje Grande (LLMs) han dificultado cada vez más la distinción entre el texto generado por máquinas y el contenido escrito por humanos, lo que ha llevado a un enfoque en la Atribución de Autoría Multilingüe (AA). Este enfoque tiene como objetivo identificar el generador específico de textos en 18 idiomas, abordando las limitaciones de los métodos de AA monolingües actuales.

Les avancées récentes dans les modèles de langage de grande taille (LLMs) rendent de plus en plus difficile la distinction entre les textes générés par des machines et ceux écrits par des humains, ce qui a conduit à un accent sur l'attribution d'auteur multilingue (AA). Cette approche vise à identifier le générateur spécifique de textes dans 18 langues, abordant les limites des méthodes AA monolingues actuelles.

Recent advancements in Large Language Models (LLMs) have made it increasingly challenging to differentiate between machine-generated text and human-written content, prompting a focus on Multilingual Authorship Attribution (AA). This approach aims to identify the specific generator of texts across 18 languages, addressing the limitations of current monolingual AA methods.