Detection of ChatGPT Fake Science with the xFakeSci Learning Algorithm

TL;DR

This paper introduces xFakeSci, a novel learning algorithm capable of distinguishing ChatGPT-generated scientific articles from authentic publications, achieving high accuracy and outperforming classical data mining methods across multiple diseases and publication periods.

Contribution

The study presents xFakeSci, a new algorithm that effectively detects AI-generated scientific content, demonstrating superior performance over traditional methods in various conditions and datasets.

Findings

xFakeSci achieved F1 scores of 80-94%.

It outperformed classical algorithms like SVM, Regression, Naive Bayes.

Calibration and proximity heuristics enhanced detection accuracy.

Abstract

Generative AI tools exemplified by ChatGPT are becoming a new reality. This study is motivated by the premise that ``AI generated content may exhibit a distinctive behavior that can be separated from scientific articles''. In this study, we show how articles can be generated using means of prompt engineering for various diseases and conditions. We then show how we tested this premise in two phases and prove its validity. Subsequently, we introduce xFakeSci, a novel learning algorithm, that is capable of distinguishing ChatGPT-generated articles from publications produced by scientists. The algorithm is trained using network models driven from both sources. As for the classification step, it was performed using 300 articles per condition. The actual label steps took place against an equal mix of 50 generated articles and 50 authentic PubMed abstracts. The testing also spanned publication periods from 2010 to 2024 and encompassed research on three distinct diseases: cancer, depression, and Alzheimer's. Further, we evaluated the accuracy of the xFakeSci algorithm against some of the classical data mining algorithms (e.g., Support Vector Machines, Regression, and Naive Bayes). The xFakeSci algorithm achieved F1 scores ranging from 80% to 94%, outperforming common data mining algorithms, which scored F1 values between 38% and 52%. We attribute the noticeable difference to the introduction of calibration and a proximity distance heuristic, which underscores this promising performance. Indeed, the prediction of fake science generated by ChatGPT presents a considerable challenge. Nonetheless, the introduction of the xFakeSci algorithm is a significant step on the way to combating fake science.