GLTR: Statistical Detection and Visualization of Generated Text
Computation and Language
2019-06-11 v1 Artificial Intelligence
Human-Computer Interaction
Machine Learning
Abstract
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
Cite
@article{arxiv.1906.04043,
title = {GLTR: Statistical Detection and Visualization of Generated Text},
author = {Sebastian Gehrmann and Hendrik Strobelt and Alexander M. Rush},
journal= {arXiv preprint arXiv:1906.04043},
year = {2019}
}
Comments
ACL 2019 Demo Track