Abstract Activation Spaces for Content-Invariant Reasoning in Large Language Models

Documenti analoghi

• HANS, are you clever? Clever Hans Effect Analysis of Neural Systems
  di: Ranaldi, Leonardo, et al.
  Pubblicazione: (2023)
• Empowering Multi-step Reasoning across Languages via Tree-of-Thoughts
  di: Ranaldi, Leonardo, et al.
  Pubblicazione: (2023)
• PreCog: Exploring the Relation between Memorization and Performance in Pre-trained Language Models
  di: Ranaldi, Leonardo, et al.
  Pubblicazione: (2023)
• Protoknowledge Shapes Behaviour of LLMs in Downstream Tasks: Memorization and Generalization with Knowledge Graphs
  di: Ranaldi, Federico, et al.
  Pubblicazione: (2025)
• Eliciting Critical Reasoning in Retrieval-Augmented Language Models via Contrastive Explanations
  di: Ranaldi, Leonardo, et al.
  Pubblicazione: (2024)