Artificial Intelligence has evolved a lot in recent years, for example in terms of language models. According to Gehrmann et al. (2019), this rapid evolution of text generation systems eventually led to increased abuse and it was with the objective of mitigating it that they decided to create the Giant Language Model Test Room (GLTR).

This tool was developed to “support humans in detecting whether a text was generated by a model" (Gehrmann et al., 2019), thus,

“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"

(Gehrmann et al., 2019)

It is an Open Source technology, the license can be consulted.

Photo by Franck V. on Unsplash.

Gehrmann, Sebastian, et al., 2019. GLTR: Statistical Detection and Visualization of Generated Text. Cornell University [online] available in: https://arxiv.org/abs/1906.04043 (acess 31 julho 2019)