GLTR:生成文本的统计检测和可视化
GLTR: Statistical Detection and Visualization of Generated Text
摘要:
随着语言模型的迅速发展,文本生成系统的滥用问题日益严重。这一进展促使开发简单的方法来检测生成的文本,可以使用和解释给非专家。我们开发了GLTR,一个工具,以支持人类在检测文本是否由模型生成。GLTR应用一套基线统计方法,可以检测常见采样方案中的生成伪影。在一项人类受试者研究中,我们表明,GLTR提供的注释方案在没有任何预先训练的情况下,将人类对虚假文本的检测率从54%提高到72%。GLTR是开源和公开部署的,已经被广泛用于检测生成的输出
英文摘要:
The rapid improvement of language models has raised the specter of abuse of text generation systems. This progress motivates the development of simple methods for detecting generated text that can be used by and explained to non-experts. We develop GLTR, a tool to support humans in detecting whether a text was generated by a model. GLTR applies a suite of baseline statistical methods that can detect generation artifacts across common sampling schemes. In a human-subjects study, we show that the annotation scheme provided by GLTR improves the human detection-rate of fake text from 54% to 72% without any prior training. GLTR is open-source and publicly deployed, and has already been widely used to detect generated outputs
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。