Evaluation Awareness Scales Predictably in Open-Weights Large Language Models

Documenti analoghi

• Alignment-Constrained Dynamic Pruning for LLMs: Identifying and Preserving Alignment-Critical Circuits
  di: Patel, Dev, et al.
  Pubblicazione: (2025)
• SALT: Steering Activations towards Leakage-free Thinking in Chain of Thought
  di: Batra, Shourya, et al.
  Pubblicazione: (2025)
• In-Context Environments Induce Evaluation-Awareness in Language Models
  di: Chaudhary, Maheep
  Pubblicazione: (2026)
• FRIT: Using Causal Importance to Improve Chain-of-Thought Faithfulness
  di: Swaroop, Anand, et al.
  Pubblicazione: (2025)
• Amortized Latent Steering: Low-Cost Alternative to Test-Time Optimization
  di: Egbuna, Nathan, et al.
  Pubblicazione: (2025)