Linear Ensembles Wash Away Watermarks: On the Fragility of Distributional Perturbations in LLMs

Ähnliche Einträge

• Soft Reasoning: Navigating Solution Spaces in Large Language Models through Controlled Embedding Exploration
  von: Zhu, Qinglin, et al.
  Veröffentlicht: (2025)
• Detecting Contextual Hallucinations in LLMs with Frequency-Aware Attention
  von: Qi, Siya, et al.
  Veröffentlicht: (2026)
• PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games
  von: Zhu, Qinglin, et al.
  Veröffentlicht: (2024)
• SymbolicThought: Integrating Language Models and Symbolic Reasoning for Consistent and Interpretable Human Relationship Understanding
  von: Zhao, Runcong, et al.
  Veröffentlicht: (2025)
• One Token Away from Collapse: The Fragility of Instruction-Tuned Helpfulness
  von: Potraghloo, Erfan Baghaei, et al.
  Veröffentlicht: (2026)