发现ChatGPT生成文本有可检测的重复概率模式，微调不影响识别。
Advancing LLM detection in the ALTA 2024 Shared Task: Techniques and Analysis
- 基于句子级概率模式检测AI生成文本
- 改写等轻微修改对检测准确率影响小
- 适合关注文本溯源与虚假信息防御的研究者
AI生成内容的泛滥催生了对可靠检测方法的需求。本研究通过句级评估，在混合文章中探索识别AI生成文本的技术。结果表明，ChatGPT-3.5 Turbo生成的内容呈现出显著且重复的概率模式，可在同域数据上实现稳定检测。实证测试显示，诸如重写等轻微文本修改对检测准确率影响极小。这些发现为推进AI检测方法提供了重要启示，指明了应对合成文本识别复杂性的可行路径。
原文摘要 · Abstract (English)
The recent proliferation of AI-generated content has prompted significant interest in developing reliable detection methods. This study explores techniques for identifying AI-generated text through sentence-level evaluation within hybrid articles. Our findings indicate that ChatGPT-3.5 Turbo exhibits distinct, repetitive probability patterns that enable consistent in-domain detection. Empirical tests show that minor textual modifications, such as rewording, have minimal impact on detection accuracy. These results provide valuable insights for advancing AI detection methodologies, offering a pathway toward robust solutions to address the complexities of synthetic text identification.
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。