对比多种神经网络模型，提升生成文本识别准确率。
Automatic detection of Gen-AI texts: A comparative framework of neural models
- 设计四种神经网络模型检测生成文本
- 在多语言和主题数据集上表现优于商用工具
- 适合需要高精度识别的学术与内容审核场景
大型语言模型的迅速普及显著增加了区分人工撰写与人工智能生成文本的难度，引发学术、编辑及社会领域的重大关切。本文通过设计、实现并比较多种基于机器学习的检测器，研究生成文本识别问题。构建了四种神经网络架构：多层感知机、一维卷积神经网络、基于MobileNet的CNN以及Transformer模型。将所提模型与广泛使用的在线检测工具（包括ZeroGPT、GPTZero、QuillBot、Originality.AI、Sapling、IsGen、Rephrase、Writer）进行对比评估。实验在COLING多语言数据集（涵盖英语与意大利语配置）以及一个聚焦艺术与心理健康主题的原创数据集上开展。结果表明，监督式检测器在不同语言和领域下表现更稳定、更鲁棒，揭示了当前检测策略的关键优势与局限性。
原文摘要 · Abstract (English)
The rapid proliferation of Large Language Models has significantly increased the difficulty of distinguishing between human-written and AI generated texts, raising critical issues across academic, editorial, and social domains. This paper investigates the problem of AI generated text detection through the design, implementation, and comparative evaluation of multiple machine learning based detectors. Four neural architectures are developed and analyzed: a Multilayer Perceptron, a one-dimensional Convolutional Neural Network, a MobileNet-based CNN, and a Transformer model. The proposed models are benchmarked against widely used online detectors, including ZeroGPT, GPTZero, QuillBot, Originality.AI, Sapling, IsGen, Rephrase, and Writer. Experiments are conducted on the COLING Multilingual Dataset, considering both English and Italian configurations, as well as on an original thematic dataset focused on Art and Mental Health. Results show that supervised detectors achieve more stable and robust performance than commercial tools across different languages and domains, highlighting key strengths and limitations of current detection strategies.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。