Circuit Component Reuse Across Tasks in Transformer Language Models

Documenti analoghi

• Language Models Implement Simple Word2Vec-style Vector Arithmetic
  di: Merullo, Jack, et al.
  Pubblicazione: (2023)
• Talking Heads: Understanding Inter-layer Communication in Transformer Language Models
  di: Merullo, Jack, et al.
  Pubblicazione: (2024)
• Transferring Linear Features Across Language Models With Model Stitching
  di: Chen, Alan, et al.
  Pubblicazione: (2025)
• Dual Process Learning: Controlling Use of In-Context vs. In-Weights Strategies with Weight Forgetting
  di: Anand, Suraj, et al.
  Pubblicazione: (2024)
• How Do Vision-Language Models Process Conflicting Information Across Modalities?
  di: Hua, Tianze, et al.
  Pubblicazione: (2025)