# GLTR: Statistical Detection and Visualization of Generated Text

## TL;DR

GLTR is a tool that uses statistical methods to help humans detect AI-generated text, significantly improving detection accuracy without prior training and supporting transparency in language model outputs.

## Contribution

The paper introduces GLTR, an open-source tool that combines statistical detection methods with visualization to assist humans in identifying generated text.

## Key findings

- Human detection rate increased from 54% to 72% with GLTR
- GLTR is effective across various sampling schemes
- The tool is widely used and publicly available

## 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