Linear Recency Bias During Training Improves Transformers' Fit to Reading Times

Ähnliche Einträge

• Frequency Explains the Inverse Correlation of Large Language Models' Size, Training Data Amount, and Surprisal's Fit to Reading Times
  von: Oh, Byung-Doh, et al.
  Veröffentlicht: (2024)
• How Well Does First-Token Entropy Approximate Word Entropy as a Psycholinguistic Predictor?
  von: Clark, Christian, et al.
  Veröffentlicht: (2025)
• The Impact of Token Granularity on the Predictive Power of Language Model Surprisal
  von: Oh, Byung-Doh, et al.
  Veröffentlicht: (2024)
• Leading Whitespaces of Language Models' Subword Vocabulary Pose a Confound for Calculating Word Probabilities
  von: Oh, Byung-Doh, et al.
  Veröffentlicht: (2024)
• The Inverse Scaling Effect of Pre-Trained Language Model Surprisal Is Not Due to Data Leakage
  von: Oh, Byung-Doh, et al.
  Veröffentlicht: (2025)