Is Grokking Worthwhile? Functional Analysis and Transferability of Generalization Circuits in Transformers

Documenti analoghi

• GEAR: A General Evaluation Framework for Abductive Reasoning
  di: He, Kaiyu, et al.
  Pubblicazione: (2025)
• HiPRAG: Hierarchical Process Rewards for Efficient Agentic Retrieval Augmented Generation
  di: Wu, Peilin, et al.
  Pubblicazione: (2025)
• Search Wisely: Mitigating Sub-optimal Agentic Searches By Reducing Uncertainty
  di: Wu, Peilin, et al.
  Pubblicazione: (2025)
• IDEA: Enhancing the Rule Learning Ability of Large Language Model Agent through Induction, Deduction, and Abduction
  di: He, Kaiyu, et al.
  Pubblicazione: (2024)
• From Reasoning to Learning: A Survey on Hypothesis Discovery and Rule Learning with Large Language Models
  di: He, Kaiyu, et al.
  Pubblicazione: (2025)