PAK-UCB Contextual Bandit: An Online Learning Approach to Prompt-Aware Selection of Generative Models and LLMs

Documenti analoghi

• A Multi-Armed Bandit Approach to Online Selection and Evaluation of Generative Models
  di: Hu, Xiaoyan, et al.
  Pubblicazione: (2024)
• PromptWise: Online Learning for Cost-Aware Prompt Assignment in Generative Models
  di: Hu, Xiaoyan, et al.
  Pubblicazione: (2025)
• An Information Theoretic Approach to Interaction-Grounded Learning
  di: Hu, Xiaoyan, et al.
  Pubblicazione: (2024)
• DAK-UCB: Diversity-Aware Prompt Routing for LLMs and Generative Models
  di: Jafari, Donya, et al.
  Pubblicazione: (2026)
• Be More Diverse than the Most Diverse: Optimal Mixtures of Generative Models via Mixture-UCB Bandit Algorithms
  di: Rezaei, Parham, et al.
  Pubblicazione: (2024)