Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads

Documenti analoghi

• Do Transformers Understand Ancient Roman Coin Motifs Better than CNNs?
  di: Reid, David, et al.
  Pubblicazione: (2026)
• Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization
  di: Wu, Junkang, et al.
  Pubblicazione: (2024)
• PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training
  di: Bobbili, Sarat Chandra, et al.
  Pubblicazione: (2025)
• LLM Agents Making Agent Tools
  di: Wölflein, Georg, et al.
  Pubblicazione: (2025)
• Active Preference Inference using Language Models and Probabilistic Reasoning
  di: Piriyakulkij, Wasu Top, et al.
  Pubblicazione: (2023)