GPT-Sentinel：区分人类生成内容和ChatGPT生成内容

GPT-Sentinel: Distinguishing Human and ChatGPT Generated Content

May 13, 2023

作者: Yutian Chen, Hao Kang, Vivian Zhai, Liangze Li, Rita Singh, Bhiksha Ramakrishnan

cs.AI

摘要

本文提出了一种新颖的方法，用于使用语言模型检测ChatGPT生成的文本与人类撰写的文本。为此，我们首先收集并发布了一个经过预处理的数据集，命名为OpenGPTText，其中包含使用ChatGPT生成的重新表述内容。然后，我们分别使用RoBERTa（Robustly Optimized BERT Pretraining Approach）和T5（Text-to-Text Transfer Transformer）设计、实现和训练了两种不同的文本分类模型。我们的模型在测试数据集上取得了显著的结果，准确率超过97％，通过各种指标进行评估。此外，我们进行了一项可解释性研究，展示了我们的模型提取和区分人类撰写文本与ChatGPT生成文本之间关键特征的能力。我们的研究结果为有效利用语言模型检测生成文本提供了重要见解。

English

This paper presents a novel approach for detecting ChatGPT-generated vs. human-written text using language models. To this end, we first collected and released a pre-processed dataset named OpenGPTText, which consists of rephrased content generated using ChatGPT. We then designed, implemented, and trained two different models for text classification, using Robustly Optimized BERT Pretraining Approach (RoBERTa) and Text-to-Text Transfer Transformer (T5), respectively. Our models achieved remarkable results, with an accuracy of over 97% on the test dataset, as evaluated through various metrics. Furthermore, we conducted an interpretability study to showcase our model's ability to extract and differentiate key features between human-written and ChatGPT-generated text. Our findings provide important insights into the effective use of language models to detect generated text.