arXiv cs.CL
· Papers
Encoding EEG Signals to Examine Human-Like Next-Word Prediction Behaviour in Language Models
arXiv:2607.16549v1 Announce Type: new Abstract: Language models (LMs) are trained to excel at predicting the next word in the sequence given prior context, and humans also share this predictability in reading comprehension. Neuroscience research reveals that next-word predictability influences brain response, as record