The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models

Documenti analoghi

• Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features
  di: Cho, Seonglae, et al.
  Pubblicazione: (2026)
• CorrSteer: Generation-Time LLM Steering via Correlated Sparse Autoencoder Features
  di: Cho, Seonglae, et al.
  Pubblicazione: (2025)
• Tool Calling is Linearly Readable and Steerable in Language Models
  di: Wu, Zekun, et al.
  Pubblicazione: (2026)
• Evaluating Explainability in Machine Learning Predictions through Explainer-Agnostic Metrics
  di: Munoz, Cristian, et al.
  Pubblicazione: (2023)
• Eliciting Personality Traits in Large Language Models
  di: Hilliard, Airlie, et al.
  Pubblicazione: (2024)