To ChatGPT, or not to ChatGPT: That is the question!

TL;DR

This study evaluates recent ChatGPT detection methods using a new benchmark dataset and finds that current techniques are ineffective at reliably distinguishing AI-generated text from human writing.

Contribution

It provides a comprehensive assessment of recent detection techniques and introduces a diverse benchmark dataset for evaluating ChatGPT detection performance.

Findings

Existing detection methods are largely ineffective.

A new benchmark dataset was curated for evaluation.

Detection accuracy remains low across methods.

Abstract

ChatGPT has become a global sensation. As ChatGPT and other Large Language Models (LLMs) emerge, concerns of misusing them in various ways increase, such as disseminating fake news, plagiarism, manipulating public opinion, cheating, and fraud. Hence, distinguishing AI-generated from human-generated becomes increasingly essential. Researchers have proposed various detection methodologies, ranging from basic binary classifiers to more complex deep-learning models. Some detection techniques rely on statistical characteristics or syntactic patterns, while others incorporate semantic or contextual information to improve accuracy. The primary objective of this study is to provide a comprehensive and contemporary assessment of the most recent techniques in ChatGPT detection. Additionally, we evaluated other AI-generated text detection tools that do not specifically claim to detect ChatGPT-generated content to assess their performance in detecting ChatGPT-generated content. For our evaluation, we have curated a benchmark dataset consisting of prompts from ChatGPT and humans, including diverse questions from medical, open Q&A, and finance domains and user-generated responses from popular social networking platforms. The dataset serves as a reference to assess the performance of various techniques in detecting ChatGPT-generated content. Our evaluation results demonstrate that none of the existing methods can effectively detect ChatGPT-generated content.