@inproceedings{tuck-verma-2025-unmasking,
    title = "Unmasking the Imposters: How Censorship and Domain Adaptation Affect the Detection of Machine-Generated Tweets",
    author = "Tuck, Bryan E.  and
      Verma, Rakesh",
    editor = "Rambow, Owen  and
      Wanner, Leo  and
      Apidianaki, Marianna  and
      Al-Khalifa, Hend  and
      Eugenio, Barbara Di  and
      Schockaert, Steven",
    booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2025.coling-main.607/",
    pages = "9044--9061",
    abstract = "The rapid development of large language models (LLMs) has significantly improved the generation of fluent and convincing text, raising concerns about their potential misuse on social media platforms. We present a comprehensive methodology for creating nine Twitter datasets to examine the generative capabilities of four prominent LLMs: Llama 3, Mistral, Qwen2, and GPT4o. These datasets encompass four censored and five uncensored model configurations, including 7B and 8B parameter base-instruction models of the three open-source LLMs. Additionally, we perform a data quality analysis to assess the characteristics of textual outputs from human, {\textquotedblleft}censored,{\textquotedblright} and {\textquotedblleft}uncensored models,{\textquotedblright} employing semantic meaning, lexical richness, structural patterns, content characteristics, and detector performance metrics to identify differences and similarities. Our evaluation demonstrates that {\textquotedblleft}uncensored{\textquotedblright} models significantly undermine the effectiveness of automated detection methods. This study addresses a critical gap by exploring smaller open-source models and the ramifications of {\textquotedblleft}uncensoring,{\textquotedblright} providing valuable insights into how domain adaptation and content moderation strategies influence both the detectability and structural characteristics of machine-generated text."
}