AI检测器足够好吗？关于机器生成文本数据集质量的调查

Are AI Detectors Good Enough? A Survey on Quality of Datasets With Machine-Generated Texts

October 18, 2024

作者: German Gritsai, Anastasia Voznyuk, Andrey Grabovoy, Yury Chekhovich

cs.AI

摘要

自回归大型语言模型（LLMs）的快速发展显著提高了生成文本的质量，这需要可靠的机器生成文本检测器。大量带有人工智能片段的检测器和数据集已经出现，根据这些数据集中的目标指标，一些检测方法甚至展现出高达99.9%的识别质量。然而，这类检测器的质量在实际应用中往往急剧下降，引发一个问题：这些检测器实际上是否非常可信，还是它们的高基准分数来自于评估数据集的质量较差？本文强调了对生成数据进行稳健和定性评估方法的需求，以抵御未来模型的偏见和低泛化能力。我们对专门用于检测人工智能生成内容的竞赛数据集进行了系统性审查，并提出了评估包含人工智能生成片段的数据集质量的方法。此外，我们讨论了利用高质量生成数据实现两个目标的可能性：改善检测模型的训练以及改善训练数据集本身。我们的贡献旨在促进更好地理解人类和机器文本之间的动态关系，从而最终支持在日益自动化的世界中信息的完整性。

English

The rapid development of autoregressive Large Language Models (LLMs) has significantly improved the quality of generated texts, necessitating reliable machine-generated text detectors. A huge number of detectors and collections with AI fragments have emerged, and several detection methods even showed recognition quality up to 99.9% according to the target metrics in such collections. However, the quality of such detectors tends to drop dramatically in the wild, posing a question: Are detectors actually highly trustworthy or do their high benchmark scores come from the poor quality of evaluation datasets? In this paper, we emphasise the need for robust and qualitative methods for evaluating generated data to be secure against bias and low generalising ability of future model. We present a systematic review of datasets from competitions dedicated to AI-generated content detection and propose methods for evaluating the quality of datasets containing AI-generated fragments. In addition, we discuss the possibility of using high-quality generated data to achieve two goals: improving the training of detection models and improving the training datasets themselves. Our contribution aims to facilitate a better understanding of the dynamics between human and machine text, which will ultimately support the integrity of information in an increasingly automated world.