類似資料

• Faithfulness Measurable Masked Language Models
  著者:: Madsen, Andreas, 等
  出版事項: (2023)
• Interpretability Needs a New Paradigm
  著者:: Madsen, Andreas, 等
  出版事項: (2024)
• Effect of Document Packing on the Latent Multi-Hop Reasoning Capabilities of Large Language Models
  著者:: Prato, Gabriele, 等
  出版事項: (2025)
• The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning
  著者:: Aghajohari, Milad, 等
  出版事項: (2025)
• Do Large Language Models Know How Much They Know?
  著者:: Prato, Gabriele, 等
  出版事項: (2025)