Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks

Ähnliche Einträge

• In-Context Language Learning: Architectures and Algorithms
  von: Akyürek, Ekin, et al.
  Veröffentlicht: (2024)
• The Surprising Effectiveness of Test-Time Training for Few-Shot Learning
  von: Akyürek, Ekin, et al.
  Veröffentlicht: (2024)
• Deductive Closure Training of Language Models for Coherence, Accuracy, and Updatability
  von: Akyürek, Afra Feyza, et al.
  Veröffentlicht: (2024)
• Implicit Representations of Grammaticality in Language Models
  von: Wang, Yingshan Susan, et al.
  Veröffentlicht: (2026)
• Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
  von: Qiu, Linlu, et al.
  Veröffentlicht: (2023)