Sample Efficient Preference Alignment in LLMs via Active Exploration

Documenti analoghi

• Sharpe Ratio-Guided Active Learning for Preference Optimization in RLHF
  di: Belakaria, Syrine, et al.
  Pubblicazione: (2025)
• Preference-Guided Diffusion for Multi-Objective Offline Optimization
  di: Annadani, Yashas, et al.
  Pubblicazione: (2025)
• Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes
  di: Belakaria, Syrine, et al.
  Pubblicazione: (2024)
• Non-Myopic Multi-Objective Bayesian Optimization
  di: Belakaria, Syrine, et al.
  Pubblicazione: (2024)
• Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effect
  di: Neopane, Ojash, et al.
  Pubblicazione: (2025)