Computational Models to Study Language Processing in the Human Brain: A Survey

TL;DR

This survey reviews how computational language models are used in brain research, emphasizing the importance of consistent evaluation and diverse datasets to understand their effectiveness in studying human language processing.

Contribution

It provides a comprehensive overview of current efforts, evaluates models on standardized datasets, and highlights the need for rigorous testing in computational neuroscience.

Findings

No single model outperforms others across all datasets

Consistent metrics are essential for fair comparison

Rich datasets and strict experimental controls are crucial

Abstract

Despite differing from the human language processing mechanism in implementation and algorithms, current language models demonstrate remarkable human-like or surpassing language capabilities. Should computational language models be employed in studying the brain, and if so, when and how? To delve into this topic, this paper reviews efforts in using computational models for brain research, highlighting emerging trends. To ensure a fair comparison, the paper evaluates various computational models using consistent metrics on the same dataset. Our analysis reveals that no single model outperforms others on all datasets, underscoring the need for rich testing datasets and rigid experimental control to draw robust conclusions in studies involving computational models.