Tokens-per-Parameter Coverage Is Critical for Robust LLM Scaling Law Extrapolation

Documenti analoghi

• Error Detection and Constraint Recovery in Hierarchical Multi-Label Classification without Prior Knowledge
  di: Kricheli, Joshua Shay, et al.
  Pubblicazione: (2024)
• SNIC bifurcation and its Application to MEMS
  di: Kricheli, Joshua Shay
  Pubblicazione: (2025)
• Consistency-based Abductive Reasoning over Perceptual Errors of Multiple Pre-trained Models in Novel Environments
  di: Leiva, Mario, et al.
  Pubblicazione: (2025)
• Revisiting SMoE Language Models by Evaluating Inefficiencies with Task Specific Expert Pruning
  di: Sarkar, Soumajyoti, et al.
  Pubblicazione: (2024)
• Diversity Measures: Domain-Independent Proxies for Failure in Language Model Queries
  di: Ngu, Noel, et al.
  Pubblicazione: (2023)