Shared Lexical Task Representations Explain Behavioral Variability In LLMs

Documenti analoghi

• Planetarium: A Rigorous Benchmark for Translating Text to Structured Planning Languages
  di: Zuo, Max, et al.
  Pubblicazione: (2024)
• Uncovering Intermediate Variables in Transformers using Circuit Probing
  di: Lepori, Michael A., et al.
  Pubblicazione: (2023)
• The dynamic interplay between in-context and in-weight learning in humans and neural networks
  di: Russin, Jacob, et al.
  Pubblicazione: (2024)
• Circuit Component Reuse Across Tasks in Transformer Language Models
  di: Merullo, Jack, et al.
  Pubblicazione: (2023)
• LLMs model how humans induce logically structured rules
  di: Loo, Alyssa, et al.
  Pubblicazione: (2025)