Polar probe linearly decodes semantic structures from LLMs

Documenti analoghi

• Probing Syntax in Large Language Models: Successes and Remaining Challenges
  di: Diego-Simón, Pablo J., et al.
  Pubblicazione: (2025)
• Emergence of Phonemic, Syntactic, and Semantic Representations in Artificial Neural Networks
  di: Orhan, Pierre, et al.
  Pubblicazione: (2026)
• A polar coordinate system represents syntax in large language models
  di: Diego-Simón, Pablo, et al.
  Pubblicazione: (2024)
• Metric Learning Encoding Models: A Multivariate Framework for Interpreting Neural Representations
  di: Jalouzot, Louis, et al.
  Pubblicazione: (2024)
• A Neural Model for Word Repetition
  di: Dager, Daniel, et al.
  Pubblicazione: (2025)