On the Salience of Low-Probability Tokens for AI-Generated Text Detection: A Multiscale Uncertainty Perspective

Documenti analoghi

• Multiscale Positive-Unlabeled Detection of AI-Generated Texts
  di: Tian, Yuchuan, et al.
  Pubblicazione: (2023)
• Training-free LLM-generated Text Detection by Mining Token Probability Sequences
  di: Xu, Yihuai, et al.
  Pubblicazione: (2024)
• Adversarial Attacks on AI-Generated Text Detection Models: A Token Probability-Based Approach Using Embeddings
  di: Kadhim, Ahmed K., et al.
  Pubblicazione: (2025)
• Exons-Detect: Identifying and Amplifying Exonic Tokens via Hidden-State Discrepancy for Robust AI-Generated Text Detection
  di: Zhu, Xiaowei, et al.
  Pubblicazione: (2026)
• ToBlend: Token-Level Blending With an Ensemble of LLMs to Attack AI-Generated Text Detection
  di: Huang, Fan, et al.
  Pubblicazione: (2024)