提出自适应距离学习方法，精准识别大模型生成文本。
Learn-to-Distance: Distance Learning for Detecting LLM-Generated Text
- 通过几何分析揭示重写检测原理，设计可自适应学习原文与改写文距离的算法。
- 在多个大模型上测试，相比最强基线提升54.3%至75.4%检测准确率。
- 适用于学术诚信、虚假信息防控，代码已开源供研究使用。
当前大型语言模型（如GPT、Claude、Gemini）生成的文本高度接近人类写作，引发虚假信息与学术不端风险，亟需可靠的检测方法。本文首先提出一种几何视角，揭示基于重写的检测算法背后的机理，并验证其泛化能力。在此基础上，我们设计一种新型重写检测算法，可自适应学习原文与改写文本之间的距离。理论上证明，自适应距离函数比固定距离更有效。实证方面，在超过100种设置下进行测试，结果表明该方法在多数场景下优于基线算法，对GPT、Claude、Gemini等目标模型，相对提升达54.3%至75.4%。相关Python实现已公开于https://github.com/Mamba413/L2D。
原文摘要 · Abstract (English)
Modern large language models (LLMs) such as GPT, Claude, and Gemini have transformed the way we learn, work, and communicate. Yet, their ability to produce highly human-like text raises serious concerns about misinformation and academic integrity, making it an urgent need for reliable algorithms to detect LLM-generated content. In this paper, we start by presenting a geometric approach to demystify rewrite-based detection algorithms, revealing their underlying rationale and demonstrating their generalization ability. Building on this insight, we introduce a novel rewrite-based detection algorithm that adaptively learns the distance between the original and rewritten text. Theoretically, we demonstrate that employing an adaptively learned distance function is more effective for detection than using a fixed distance. Empirically, we conduct extensive experiments with over 100 settings, and find that our approach demonstrates superior performance over baseline algorithms in the majority of scenarios. In particular, it achieves relative improvements from 54.3% to 75.4% over the strongest baseline across different target LLMs (e.g., GPT, Claude, and Gemini). A python implementation of our proposal is publicly available at https://github.com/Mamba413/L2D.
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。