Documenti analoghi

• Leading Whitespaces of Language Models' Subword Vocabulary Pose a Confound for Calculating Word Probabilities
  di: Oh, Byung-Doh, et al.
  Pubblicazione: (2024)
• The Impact of Token Granularity on the Predictive Power of Language Model Surprisal
  di: Oh, Byung-Doh, et al.
  Pubblicazione: (2024)
• Linear Recency Bias During Training Improves Transformers' Fit to Reading Times
  di: Clark, Christian, et al.
  Pubblicazione: (2024)
• The Inverse Scaling Effect of Pre-Trained Language Model Surprisal Is Not Due to Data Leakage
  di: Oh, Byung-Doh, et al.
  Pubblicazione: (2025)
• Frequency Explains the Inverse Correlation of Large Language Models' Size, Training Data Amount, and Surprisal's Fit to Reading Times
  di: Oh, Byung-Doh, et al.
  Pubblicazione: (2024)