Frequency Explains the Inverse Correlation of Large Language Models’ Size, Training Data Amount, and Surprisal’s Fit to Reading Times

Frequency Explains the Inverse Correlation of Large Language Models’ Size, Training Data Amount, and Surprisal’s Fit to Reading Times Byung-Doh Oh author Shisen Yue author William Schuler author 2024-03 text Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers) Yvette Graham editor Matthew Purver editor Association for Computational Linguistics St. Julian’s, Malta conference publication oh-etal-2024-frequency 10.18653/v1/2024.eacl-long.162 https://aclanthology.org/2024.eacl-long.162/ 2024-03 2644 2663