AuTexTification Dataset (Full data)

Datasets of the AuTexTification shared task at IberLEF 2023. This task aims to boost research on the detection of text generated automatically by text generation models. Participants must develop models that exploit clues about linguistic form and meaning to distinguish automatically generated text from human text. This dataset includes the training and test splits with labels for all the subtasks and languages. Additionally, each file includes the domain, the model and the prompt used to generate each sample. The model label mapping for subtask 2 is: {"A": "bloom-1b7", "B": "bloom-3b", "C": "bloom-7b1", "D": "babbage", "E": "curie", "F": "text-davinci-003"}

本数据集为IberLEF 2023年AuTexTification共享任务的配套数据集。该任务旨在推动文本生成模型自动生成文本的检测相关研究。参赛队伍需开发可挖掘语言形式与语义线索的模型，以区分自动生成文本与人类创作文本。本数据集涵盖了覆盖所有子任务与语种的带标签训练集与测试集划分。此外，每份数据文件均记录了生成对应样本所使用的领域、模型与提示词（prompt）。子任务2的模型标签映射关系如下：{"A": "bloom-1b7", "B": "bloom-3b", "C": "bloom-7b1", "D": "babbage", "E": "curie", "F": "text-davinci-003"}