**摘要**
随着人工智能写作助手越来越多地集成到现实世界的起草和修订工作流程中,许多文档不再是纯粹的人工编写或人工智能生成的,而是由渐进的人工智能共同编辑产生的。然而,现有的人工智能文本检测基准主要集中在最终输出上,对人工智能作者身份信号如何出现、积累或消失的理解有限
👤 作者: Sondos Mahmoud Bsharat, Jiacheng Liu, Xiaohan Zhao, Tianjun Yao, Xinyi Shang, Yi Tang, Jiacheng Cui, Ahmed Elhagry, Salwa K. Al Khatib, Hao Li, Salman Khan, Zhiqiang Shen
---
🔗 **[Operation-Guided Progressive Human-to-AI Text Transformation Benchmark for Multi-Granularity AI-Text Detection](https://arxiv.org/abs/2606.06481v1)**
> Operation-Guided Progressive Human-to-AI Text Transformation Benchmark for Multi-Granularity AI-Text Detection
🏷️ 来源: ArXiv cs.AI
⏱️ 2026-06-05 14:01
news
Operation-Guided Progressive Human-to-AI Text Transformation Benchmark for Multi-Granularity AI-Text Detection
加载回复中...