detectors: Predictions from GPT Detectors

In detectors: Prediction Data from GPT Detectors

Predictions from GPT Detectors

Description

Data derived from the paper GPT detectors are biased against non-native English writers. The study authors carried out a series of experiments passing a number of essays to different GPT detection models. Juxtaposing detector predictions for papers written by native and non-native English writers, the authors argue that GPT detectors disproportionately classify real writing from non-native English writers as AI-generated.

Usage

detectors

Format

A data frame with 6,185 rows and 9 columns:

kind

Whether the essay was written by a "Human" or "AI".

.pred_AI

The class probability from the GPT detector that the inputted text was written by AI.

.pred_class

The uncalibrated class prediction, encoded as if_else(.pred_AI > .5, "AI", "Human")

detector

The name of the detector used to generate the predictions.

native

For essays written by humans, whether the essay was written by a native English writer or not. These categorizations are coarse; values of "Yes" may actually be written by people who do not write with English natively. NA indicates that the text was not written by a human.

name

A label for the experiment that the predictions were generated from.

model

For essays that were written by AI, the name of the model that generated the essay.

document_id

A unique identifier for the supplied essay. Some essays were supplied to multiple detectors. Note that some essays are AI-revised derivatives of others.

prompt

For essays that were written by AI, a descriptor for the form of "prompt engineering" passed to the model.

For more information on these data, see the source paper.

Source

\Sexpr[results=rd]{tools:::Rd_expr_doi("10.1016/j.patter.2023.100779")}

Examples

detectors

detectors documentation built on Oct. 26, 2023, 5:09 p.m.