Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase. Therefore, it is vital to detect the contamination by checking whether an LLM has been pre-trained on the target texts. Recent studies focus on the generated texts and compute perplexities, which are superficial features and not reliable. In this study, we propose to utilize the probing technique for pre-training data detection by examining the model's internal activations. Our method is simple and effective and leads to more trustworthy pre-training data detection. Additionally, we propose ArxivMIA, a new challenging benchmark comprising arxiv abstracts from Computer Science and Mathematics categories. Our experiments demonstrate that our method outperforms all baselines, and achieves state-of-the-art performance on both WikiMIA and ArxivMIA, with additional experiments confirming its efficacy (Our code and dataset are available at https://github.com/zhliu0106/probing-lm-data).

大语言模型（LLMs）在展示其出色的能力的同时，也引发了由于隐私问题和基准数据集泄露所导致的数据污染问题。因此，在预训练阶段检测污染是否有LLM在目标文本上进行了预训练变得至关重要。最近的研究关注生成的文本并计算困惑度，但这些都是表面特征而不可靠。本研究提出利用探测技术来检测预训练数据，通过检查模型的内部激活状态。我们的方法简单且有效，并实现了更可靠的预训练数据检测。此外，我们还提出了ArxivMIA基准，它包括来自计算机科学和数学类别的arxiv摘要。我们的实验证明我们的方法胜过所有基准，实现了WikiMIA和ArxivMIA的最新性能，并通过额外的实验验证了其有效性。

对预训练数据检测的语言模型探究