@inproceedings{2fec2012e14a42d3b8d169b252edc8c3,
title = "Crafting Tomorrow{\textquoteright}s Headlines: Neural News Generation and Detection in English, Turkish, Hungarian, and Persian",
abstract = "In an era dominated by information overload and its facilitation with Large Language Models (LLMs), the prevalence of misinformation poses a significant threat to public discourse and societal well-being. A critical concern at present involves the identification of machine-generated news. In this work, we take a significant step by introducing a benchmark dataset designed for neural news detection in four languages: English, Turkish, Hungarian, and Persian. The dataset incorporates outputs from multiple multilingual generators (in both zero-shot and fine-tuned setups) such as BloomZ, LLaMa-2, Mistral, Mixtral, and GPT-4. Next, we experiment with a variety of classifiers, ranging from those based on linguistic features to advanced Transformer-based models and LLMs prompting. We present the detection results aiming to delve into the interpretability and robustness of machine-generated text detectors across all target languages.",
author = "Cem {\"U}y{\"u}k and Danica Rov{\'o} and Shaghayegh Kolli and Rabia Varol and Georg Groh and Daryna Dementieva",
note = "Publisher Copyright: {\textcopyright} 2024 Association for Computational Linguistics.; 3rd Workshop on NLP for Positive Impact, NLP4PI 2024, held in conjunction with the 2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024 ; Conference date: 15-11-2024",
year = "2024",
language = "English",
series = "NLP4PI 2024 - 3rd Workshop on NLP for Positive Impact, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "271--307",
editor = "Daryna Dementieva and Oana Ignat and Zhijing Jin and Zhijing Jin and Rada Mihalcea and Giorgio Piatti and Joel Tetreault and Steven Wilson and Jieyu Zhao",
booktitle = "NLP4PI 2024 - 3rd Workshop on NLP for Positive Impact, Proceedings of the Workshop",
}