Permute-and-Flip: An optimally stable and watermarkable decoder for LLMs

Documenti analoghi

• The Landscape of Memorization in LLMs: Mechanisms, Measurement, and Mitigation
  di: Xiong, Alexander, et al.
  Pubblicazione: (2025)
• Proving membership in LLM pretraining data via data watermarks
  di: Wei, Johnny Tian-Zheng, et al.
  Pubblicazione: (2024)
• Are You Getting What You Pay For? Auditing Model Substitution in LLM APIs
  di: Cai, Will, et al.
  Pubblicazione: (2025)
• WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
  di: Giboulot, Eva, et al.
  Pubblicazione: (2024)
• Improving LLM Safety Alignment with Dual-Objective Optimization
  di: Zhao, Xuandong, et al.
  Pubblicazione: (2025)