Language models and brain alignment: beyond word-level semantics and prediction

by   Gabriele Merlin, et al.

Pretrained language models that have been trained to predict the next word over billions of text documents have been shown to also significantly predict brain recordings of people comprehending language. Understanding the reasons behind the observed similarities between language in machines and language in the brain can lead to more insight into both systems. Recent works suggest that the prediction of the next word is a key mechanism that contributes to the alignment between the two. What is not yet understood is whether prediction of the next word is necessary for this observed alignment or simply sufficient, and whether there are other shared mechanisms or information that is similarly important. In this work, we take a first step towards a better understanding via two simple perturbations in a popular pretrained language model. The first perturbation is to improve the model's ability to predict the next word in the specific naturalistic stimulus text that the brain recordings correspond to. We show that this indeed improves the alignment with the brain recordings. However, this improved alignment may also be due to any improved word-level or multi-word level semantics for the specific world that is described by the stimulus narrative. We aim to disentangle the contribution of next word prediction and semantic knowledge via our second perturbation: scrambling the word order at inference time, which reduces the ability to predict the next word, but maintains any newly learned word-level semantics. By comparing the alignment with brain recordings of these differently perturbed models, we show that improvements in alignment with brain recordings are due to more than improvements in next word prediction and word-level semantics.


page 6

page 10

page 17

page 19

page 21


Joint processing of linguistic properties in brains and language models

Language models have been shown to be very effective in predicting brain...

Modeling Task Effects on Meaning Representation in the Brain via Zero-Shot MEG Prediction

How meaning is represented in the brain is still one of the big open que...

Training language models for deeper understanding improves brain alignment

Building systems that achieve a deeper understanding of language is one ...

Clinical Text Prediction with Numerically Grounded Conditional Language Models

Assisted text input techniques can save time and effort and improve text...

Word-As-Image for Semantic Typography

A word-as-image is a semantic typography technique where a word illustra...

Does injecting linguistic structure into language models lead to better alignment with brain recordings?

Neuroscientists evaluate deep neural networks for natural language proce...

Adapting Transformer Language Models for Predictive Typing in Brain-Computer Interfaces

Brain-computer interfaces (BCI) are an important mode of alternative and...

Please sign up or login with your details

Forgot password? Click here to reset