Don't Always Pick the Highest-Performing Model: An Information Theoretic View of LLM Ensemble Selection

Documenti analoghi

• Balancing Information Accuracy and Response Timeliness in Networked LLMs
  di: Turkmen, Yigit, et al.
  Pubblicazione: (2025)
• FedGrAINS: Personalized SubGraph Federated Learning with Adaptive Neighbor Sampling
  di: Ceyani, Emir, et al.
  Pubblicazione: (2025)
• Maverick-Aware Shapley Valuation for Client Selection in Federated Learning
  di: Yang, Mengwei, et al.
  Pubblicazione: (2024)
• Learned Digital Codes for Over-the-Air Computation in Federated Edge Learning
  di: Tarizzo, Antonio, et al.
  Pubblicazione: (2025)
• Robust Regression with Ensembles Communicating over Noisy Channels
  di: Ben-Hur, Yuval, et al.
  Pubblicazione: (2024)