基于注意力图拓扑结构的人工文本检测
Artificial Text Detection via Examining the Topology of Attention Maps
摘要：
最近的生成模型具有令人印象深刻的能力，可以创建具有挑战性的文本，这些文本很难与人类编写的文本区分开来，可能会被滥用来生成假新闻，产品评论，甚至滥用内容。尽管现有的人工文本检测方法性能突出，但它们仍然缺乏对未知模型的可解释性和鲁棒性。为此，我们提出了三种新的类型的可解释的拓扑特征的基础上，拓扑数据分析（TDA），这是目前在自然语言处理领域的研究。我们的经验表明，来自BERT模型的功能优于计数和基于神经的基线高达10%的三个常见的数据集，并往往是最强大的对看不见的GPT风格的生成模型，而不是现有的方法。对这些特征的探索性分析揭示了它们对表层特征和句法特征的敏感性。结果表明，TDA是一个很有前途的线相对于NLP任务，特别是那些将表面和结构信息。
英文摘要：
The impressive capabilities of recent generative models to create texts that are challenging to distinguish from the human-written ones can be misused for generating fake news, product reviews, and even abusive content. Despite the prominent performance of existing methods for artificial text detection, they still lack interpretability and robustness towards unseen models. To this end, we propose three novel types of interpretable topological features for this task based on Topological Data Analysis (TDA) which is currently understudied in the field of NLP. We empirically show that the features derived from the BERT model outperform count- and neural-based baselines up to 10\% on three common datasets, and tend to be the most robust towards unseen GPT-style generation models as opposed to existing methods. The probing analysis of the features reveals their sensitivity to the surface and syntactic properties. The results demonstrate that TDA is a promising line with respect to NLP tasks, specifically the ones that incorporate surface and structural information.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
