Energy from energy-based transformers predicts reading times better than surprisal alone and captures subject/object relative clause asymmetries while subsuming attention-entropy effects.
Probabilistic Predictions of People Perusing: Evaluating Metrics of Language Model Performance for Psycholinguistic Modeling
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Energy-Based Transformers as Predictors of Reading Difficulty
Energy from energy-based transformers predicts reading times better than surprisal alone and captures subject/object relative clause asymmetries while subsuming attention-entropy effects.