cs.CLNov 19, 2026

The Depth of a Prediction: Where Language Models Resolve a Word Predicts Human Reading Time

Authors: Donato Riccio, Fabrizio Maturo

Organizations: Department of Engineering and Science, Universitas Mercatorum, Rome, Italy · Department of Economics, Statistics and Business, Universitas Mercatorum, Rome, Italy

Abstract

Surprisal from a language model's final layer predicts how long people read a word, yet the model computes its prediction across many layers. We read each word's prediction at every layer with the tuned lens and summarize this layerwise surprisal trajectory by its resolution depth, the depth around which its change is centered. On eight English eye-tracking and self-paced reading corpora (81,957 words) and ten GPT-2, OPT and Pythia models, words that a model resolves later, and the words after them, are read more slowly than equally surprising words. Resolution depth improves held-out prediction beyond final-layer surprisal, entropy and the best single layer by 0.26 millinats per word (pooled p = 0.001), about a third of entropy's gain, and each model family gains, GPT-2 and Pythia through one corpus each. The net gain varies between corpora (random-effects mean 0.07, p = 0.37); against layer-shuffled depth, which adds as many coefficients, it is positive in seven of eight corpora (random-effects mean 0.23, p = 0.016), and untrained networks show no gain under the logit lens. Pooled over corpora, the effect holds with corrected word probabilities and beyond first-to-last-layer divergences, and a whole-trajectory functional regression adds no significant information beyond resolution depth.

Figures & tables

Appendix figures & tables5 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Probing for Reading Times

    Apr 20, 2026Eleftheria Tsipidi, Samuel Kiegeland, Francesco Ignazio Re +4Computational PsycholinguisticsLanguage Model Probing

  2. Reader Proficiency Shapes Layer-wise Surprisal Profiles

    Sep 29, 2026Akio Hayakawa, Horacio SaggionLanguage Model Probing

  3. A Systematic Analysis of the Predictive Power of LM Surprisal in Reading Chinese

    Oct 4, 2026Hongao Zhu, Muxiaoqiao Xu, Yikang Liu +4Language Model Scaling LawsLanguage Modeling