The Reasoning-Memorization Interplay in Language Models Is Mediated by a Single Direction

Documenti analoghi

• Corrupted by Reasoning: Reasoning Language Models Become Free-Riders in Public Goods Games
  di: Piedrahita, David Guzman, et al.
  Pubblicazione: (2025)
• Causality for Natural Language Processing
  di: Jin, Zhijing
  Pubblicazione: (2025)
• Intrinsic Test of Unlearning Using Parametric Knowledge Traces
  di: Hong, Yihuai, et al.
  Pubblicazione: (2024)
• Refusal in Language Models Is Mediated by a Single Direction
  di: Arditi, Andy, et al.
  Pubblicazione: (2024)
• Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning
  di: Xu, Ruoxi, et al.
  Pubblicazione: (2025)