Importance Sampling is All You Need: Predict LLM's performance on new benchmark by reusing existing benchmark

Documenti analoghi

• Project MPG: towards a generalized performance benchmark for LLM capabilities
  di: Spangher, Lucas, et al.
  Pubblicazione: (2024)
• How predictable is language model benchmark performance?
  di: Owen, David
  Pubblicazione: (2024)
• Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families
  di: Polo, Felipe Maia, et al.
  Pubblicazione: (2024)
• Agents Are All You Need for LLM Unlearning
  di: Sanyal, Debdeep, et al.
  Pubblicazione: (2025)
• Forget Attention: Importance-Aware Attention Is All You Need
  di: Shin, Soohyeong, et al.
  Pubblicazione: (2026)