This paper presents the MasonTigers entry to the SemEval-2024 Task 8 -
Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text
Detection. The task encompasses Binary Human-Written vs. Machine-Generated Text
Classification (Track A), Multi-Way Machine-Generated Text Classification
(Track B), and Human-Machine Mixed Text Detection (Track C). Our best
performing approaches utilize mainly the ensemble of discriminator transformer
models along with sentence transformer and statistical machine learning
approaches in specific cases. Moreover, zero-shot prompting and fine-tuning of
FLAN-T5 are used for Track A and B.

这篇论文介绍了 MasonTigers 参与 SemEval-2024 任务 8，即多生成器、多域和多语言黑盒机器生成文本检测。该任务包括二进制的人工书写 vs. 机器生成文本分类（A 轨道），多种机器生成文本分类（B 轨道）和人机混合文本检测（C 轨道）。我们最好的方法主要使用鉴别器转换模型的集成，以及句子转换模型和统计机器学习方法在特定情况下。此外，对于 A 轨道和 B 轨道，还使用了零样本提示和 FLAN-T5 的微调。