Alignment Faking - the Train -> Deploy Asymmetry: Through a Game-Theoretic Lens with Bayesian-Stackelberg Equilibria

Documenti analoghi

• TRACEALIGN -- Tracing the Drift: Attributing Alignment Failures to Training-Time Belief Sources in LLMs
  di: Das, Amitava, et al.
  Pubblicazione: (2025)
• Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types
  di: Sinha, Neelabh, et al.
  Pubblicazione: (2024)
• Are Small Language Models Ready to Compete with Large Language Models for Practical Applications?
  di: Sinha, Neelabh, et al.
  Pubblicazione: (2024)
• AlignGuard-LoRA: Alignment-Preserving Fine-Tuning via Fisher-Guided Decomposition and Riemannian-Geodesic Collision Regularization
  di: Das, Amitava, et al.
  Pubblicazione: (2025)
• Stochastic CHAOS: Why Deterministic Inference Kills, and Distributional Variability Is the Heartbeat of Artifical Cognition
  di: Joshi, Tanmay, et al.
  Pubblicazione: (2026)