2026-07-21 04:00 UTCOriginal source2 min readUpdated: 2026-07-21 08:27 UTC

Encoding EEG Signals to Examine Human-Like Next-Word Prediction Behaviour in Language Models

This study compares human and language model (LM) next-word prediction using EEG event-related potentials (ERPs), finding that only the 'surprisal' measure correlates with language-processing ERPs, especially for open-class words, and that scaling LMs does not guarantee more human-like cognitive processing.

SourcearXiv Computational LinguisticsAuthor: Boi Mai Quach, Binh T. Nguyen, Cathal Gurrin, Graham Healy

Article intelligence

EngineersAdvanced

Key points

LMs approach human accuracy in next-word prediction, but high accuracy may not reflect cognitive signals of reading comprehension.
Two information measures (top-1 prediction and surprisal) were used to model ERP patterns and assess cognitive plausibility of LMs.
Only surprisal correlated with language-processing ERPs, particularly for open-class words with high semantic content.
Challenges the assumption that scaling up model parameters and compute consistently improves human-like language processing.

Why it matters

This matters because lMs approach human accuracy in next-word prediction, but high accuracy may not reflect cognitive signals of reading comprehension.

Technical impact

May affect model selection, inference cost, product capability, and evaluation benchmarks.

This panel is AI-generated and reviewed for accuracy.

-->

[Submitted on 17 Jul 2026]

Title:Encoding EEG Signals to Examine Human-Like Next-Word Prediction Behaviour in Language Models

View a PDF of the paper titled Encoding EEG Signals to Examine Human-Like Next-Word Prediction Behaviour in Language Models, by Boi Mai Quach and 3 other authors

View PDF HTML (experimental)

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 recorded at millisecond resolution using electroencephalography (EEG). While our evidence indicates that advanced LMs achieve accuracies closely aligned with human performance at the next-word prediction task, this raises the question: Does higher prediction accuracy necessarily mean that these models adequately capture the cognitive signals associated with human reading comprehension? Here, we generate regressors for both humans and LMs based on two information measures, including top-1 prediction and surprisal, to predict event-related potential (ERP) elicited from EEG recordings which reflect different stages of cognitive processing during reading. We argue that modelling ERP patterns offers fine-grained analysis of the cognitive plausibility of various LMs during reading. Our results indicate that only surprisal potentially correlates with language-processing ERPs, especially for open-class words with high semantic content. Moreover, our findings challenge the assumption that scaling LMs with increased parameters and computational budgets will consistently lead to improved convergence with human-like linguistic processing.

Subjects:

Computation and Language (cs.CL)

Cite as: arXiv:2607.16549 [cs.CL]

(or arXiv:2607.16549v1 [cs.CL] for this version)

https://doi.org/10.48550/arXiv.2607.16549

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mai-Boi Quach [view email] [v1] Fri, 17 Jul 2026 23:11:16 UTC (5,268 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled Encoding EEG Signals to Examine Human-Like Next-Word Prediction Behaviour in Language Models, by Boi Mai Quach and 3 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.CL

new | recent | 2026-07

Change to browse by:

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Data provided by:

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)